Which AI models can I run on an RTX 4090?

545 of the 829 LLMs analyzed on Model Anatomy fit on an RTX 4090 (21.6 GB usable) with at least 32K tokens of context, using a 8-bit context cache. Each row shows the best file that fits and how much context the remaining memory holds.

Hardware

How many

Context needed

Context cache

Sort by

Show models that don't fit

Model	Params	File that fits	Context that fits
Qwen/Qwen3-0.6BDense	752M596M active	As published1.50 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-VL-8B-InstructDense + vision	8.77B7.57B active	As published17.5 GB of 21.6 GB available	≈ 54K tokensmax 256K
Qwen/Qwen3-8BDense	8.19B	As published16.4 GB of 21.6 GB available	Full 40K
unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUFMoE	30.5B3.04B active	Q4_119.2 GB of 21.6 GB available	≈ 48K tokensmax 256K
google/gemma-4-26B-A4B-itMoE + vision	25.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
Qwen/Qwen2.5-7B-InstructDense	7.62B	As published15.2 GB of 21.6 GB available	Full 32K
Qwen/Qwen3.5-9BDense + vision	9.65B8.18B active	As published19.3 GB of 21.6 GB available	≈ 134K tokensmax 256K
google/gemma-4-31B-itDense + vision	31.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 43K tokensmax 256K
Qwen/Qwen2.5-0.5B-InstructDense	494M	As published988 MB of 21.6 GB available	Full 32K
Qwen/Qwen3.8-27BDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen2.5-1.5B-InstructDense	1.54B	As published3.09 GB of 21.6 GB available	Full 32K
Qwen/Qwen3-4BDense	4.02B	As published8.04 GB of 21.6 GB available	Full 40K
Qwen/Qwen3.5-4BDense + vision	4.66B	As published9.32 GB of 21.6 GB available	Full 256K
Qwen/Qwen2.5-VL-7B-InstructDense + vision	8.29B7.07B active	As published16.6 GB of 21.6 GB available	Full 125K
openai/gpt-oss-20bMoE	20.9B3.61B active	As published13.8 GB of 21.6 GB available	Full 128K
ornith-ai/Ornith-1.5-9B-GGUFDense	9.20B7.94B active	BF1618.4 GB of 21.6 GB available	≈ 187K tokensmax 256K
Qwen/Qwen2.5-3B-InstructDense	3.09B	As published6.17 GB of 21.6 GB available	Full 32K
Qwen/Qwen3.8-27B-FP8Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUFMoE	35.5B2.95B active	Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-019.9 GB of 21.6 GB available	≈ 153K tokensmax 256K
Qwen/Qwen3.5-2BDense + vision	2.27B1.94B active	As published4.55 GB of 21.6 GB available	Full 256K
lmstudio-community/Qwen3.8-27B-MLX-4bitDense + vision	27.4B	As published16.1 GB of 21.6 GB available	≈ 161K tokensmax 256K
lmstudio-community/Qwen3.8-27B-MLX-8bitDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
lmstudio-community/Qwen3.8-27B-MLX-6bitDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
lmstudio-community/Qwen3.8-27B-MLX-5bitDense + vision	27.4B	As published19.4 GB of 21.6 GB available	≈ 61K tokensmax 256K
Qwen/Qwen3.6-35B-A3BMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
Qwen/Qwen3.6-35B-A3B-FP8MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
Qwen/Qwen3-4B-Instruct-2507Dense	4.02B	As published8.04 GB of 21.6 GB available	≈ 180K tokensmax 256K
Qwen/Qwen3-1.7BDense	2.03B1.72B active	As published4.06 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-VL-4B-InstructDense + vision	4.44B	As published8.88 GB of 21.6 GB available	≈ 169K tokensmax 256K
RadixArk/Kimi-K3-DSpark	2.25B	As published4.50 GB of 21.6 GB available	Full 1M
Qwen/Qwen2.5-7B-Instruct-AWQDense	7.62B	As published5.57 GB of 21.6 GB available	Full 32K
ornith-ai/Ornith-1.0-9B-GGUFDense	8.95B7.94B active	BF1617.9 GB of 21.6 GB available	≈ 216K tokensmax 256K
farbodtavakkoli/OTel-2.0-Decision-26B-A4B-4bitMoE + vision	25.8B	As published17.2 GB of 21.6 GB available	≈ 205K tokensmax 256K
Qwen/Qwen3-VL-2B-InstructDense + vision	2.13B1.72B active	As published4.26 GB of 21.6 GB available	Full 256K
datalab-to/chandra-ocr-2Dense + vision	5.30B4.33B active	As published10.6 GB of 21.6 GB available	Full 256K
Qwen/Qwen2.5-Coder-7B-InstructDense	7.62B	As published15.2 GB of 21.6 GB available	Full 32K
Qwen/Qwen3-14B-AWQDense	14.8B	As published9.98 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-VL-8B-Instruct-FP8Dense + vision	8.77B7.57B active	As published10.6 GB of 21.6 GB available	≈ 146K tokensmax 256K
Qwen/Qwen2.5-VL-3B-InstructDense + vision	3.75B3.09B active	As published7.51 GB of 21.6 GB available	Full 125K
Qwen/Qwen3.5-0.8BDense + vision	873M773M active	As published1.75 GB of 21.6 GB available	Full 256K
Qwen/Qwen2.5-14B-InstructDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 32K
Qwen/Qwen3.6-27BDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
JonathanColetti/Qwen3.8-27B-Uncensored-GGUFDense	27.3B	Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFDense	27.3B	Q5_K20.2 GB of 21.6 GB available	≈ 37K tokensmax 256K
ornith-ai/Ornith-1.0-35B-GGUFMoE	34.7B2.95B active	Q4_K_M21.2 GB of 21.6 GB available	≈ 35K tokensmax 256K
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUFDense	27.3B	Q5_K19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUFDense	9.20B7.94B active	BF1618.4 GB of 21.6 GB available	≈ 187K tokensmax 256K
Qwen/Qwen2.5-14B-Instruct-AWQDense	14.8B	As published9.98 GB of 21.6 GB available	Full 32K
Qwen/Qwen2-VL-2B-InstructDense + vision	2.21B1.54B active	As published4.42 GB of 21.6 GB available	Full 32K
ornith-ai/Ornith-1.0-35BMoE + vision	35.1B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 170K tokensmax 256K
Qwen/Qwen2.5-VL-7B-Instruct-AWQDense + vision	8.29B7.07B active	As published6.92 GB of 21.6 GB available	Full 125K
Qwen/Qwen3.5-35B-A3BMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive	7.52B	Q8_K8.13 GB of 21.6 GB available	Full 128K
Qwen/Qwen3.5-27BDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-14BDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
zai-org/GLM-4.7-FlashMoE	31.2B3.58B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 146K tokensmax 198K
Qwen/Qwen2.5-Coder-14B-InstructDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 32K
Qwen/Qwen3-30B-A3BMoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
Qwen/Qwen3-8B-AWQDense	8.19B	As published6.10 GB of 21.6 GB available	Full 40K
mistralai/Mistral-7B-Instruct-v0.2Dense	7.24B	As published14.5 GB of 21.6 GB available	Full 32K
0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUFDense	26.9B	RVN-Q5_K_M-multilingual-mtp19.7 GB of 21.6 GB available	≈ 53K tokensmax 256K
prism-ml/Ternary-Bonsai-2-27B-ggufDense	26.9B	Ternary-Bonsai-2-27B-Q2_07.63 GB of 21.6 GB available	Full 256K
unsloth/Qwen3.6-27B-NVFP4Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen2-VL-7B-Instruct-AWQDense + vision	8.29B7.07B active	As published6.92 GB of 21.6 GB available	Full 32K
Qwen/Qwen3.5-35B-A3B-FP8MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
Qwen/Qwen2.5-0.5BDense	494M	As published988 MB of 21.6 GB available	Full 32K
autotrust/JEV-27B-VLDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-4B-BaseDense	4.02B	As published8.04 GB of 21.6 GB available	Full 32K
unsloth/Qwen3.5-9B-GGUFDense	8.95B7.94B active	BF1617.9 GB of 21.6 GB available	≈ 216K tokensmax 256K
Qwen/Qwen3-1.7B-BaseDense	1.72B	As published3.44 GB of 21.6 GB available	Full 32K
Qwen/Qwen3.6-27B-FP8Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUFDense	27.3B	Qwen3.8-27B-TurboFCFusion-735-882-Here-Uncen-NEO-CODER-MAX-Q5_K_S20.2 GB of 21.6 GB available	≈ 38K tokensmax 256K
peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUFDense	27.3B	UD-Q4_K_XL17.6 GB of 21.6 GB available	≈ 116K tokensmax 256K
unsloth/Qwen3.6-35B-A3B-NVFP4MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
sahilchachra/Unlimited-OCR-AWQMoE + vision	3.34B672M active	As published2.82 GB of 21.6 GB available	Full 32K
unsloth/Qwen3.6-35B-A3B-GGUFMoE	34.7B2.95B active	UD-Q4_K_S20.9 GB of 21.6 GB available	≈ 61K tokensmax 256K
OBLITERATUS/Qwen3.8-27B-OBLITERATEDDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
ggml-org/Qwen3.8-27B-GGUFDense	26.9B	Q4_K_M19.4 GB of 21.6 GB available	≈ 61K tokensmax 256K
datalab-to/surya-ocr-2Dense + vision	686M586M active	As published1.37 GB of 21.6 GB available	Full 256K
LiquidAI/LFM2.5-2.6B-GGUF	2.70B	BF165.40 GB of 21.6 GB available	Full 128K
Qwen/Qwen2.5-Coder-14B-Instruct-AWQDense	14.8B	As published9.98 GB of 21.6 GB available	Full 32K
ornith-ai/Ornith-1.0-9BDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
unsloth/Qwen3.6-27B-MTP-GGUFDense	27.3B	UD-Q5_K_XL20.4 GB of 21.6 GB available	≈ 33K tokensmax 256K
QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQMoE + vision	31.1B3.04B active	As published17.9 GB of 21.6 GB available	≈ 74K tokensmax 256K
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUFDense	27.3B	IQ3_S12.1 GB of 21.6 GB available	Full 256K
baidu/Unlimited-OCRMoE + vision	3.34B672M active	As published6.67 GB of 21.6 GB available	Full 32K
Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8MoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 88K tokensmax 256K
datalab-to/surya-ocr-2-ggufDense	632M565M active	surya-21.27 GB of 21.6 GB available	Full 256K
unsloth/Qwen3.6-27B-GGUFDense	26.9B	UD-Q5_K_XL20.0 GB of 21.6 GB available	≈ 42K tokensmax 256K
openbmb/MiniCPM5-2BDense	2.52B2.25B active	As published5.03 GB of 21.6 GB available	Full 128K
mlx-community/Llama-3.1-8B-Instruct-4bitDense	8.03B	As published4.52 GB of 21.6 GB available	Full 128K
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUFDense	27.3B	Q4_K_M18.5 GB of 21.6 GB available	≈ 88K tokensmax 256K
unsloth/Qwen3.6-35B-A3B-MTP-GGUFMoE	35.5B2.95B active	UD-IQ4_NL18.5 GB of 21.6 GB available	Full 256K
legraphista/glm-4-9b-chat-IMat-GGUFDense	9.40B	BF1618.8 GB of 21.6 GB available	Full 128K
QuantTrio/Qwen3.5-9B-AWQDense + vision	9.65B8.18B active	As published12.4 GB of 21.6 GB available	Full 256K
bartowski/endless-frontier_BigBang-v1-GGUFMoE	35.5B2.95B active	Q4_K_S21.1 GB of 21.6 GB available	≈ 45K tokensmax 256K
RedHatAI/Qwen3.6-35B-A3B-NVFP4MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-AggressiveMoE	34.7B2.95B active	Q4_K_M21.2 GB of 21.6 GB available	≈ 35K tokensmax 256K
cyankiwi/Qwen3.6-27B-AWQ-INT4Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
RedHatAI/gemma-4-26B-A4B-it-FP8-dynamicMoE + vision	26.5B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
Qwen/Qwen3-4B-Instruct-2507-FP8Dense	4.41B	As published5.19 GB of 21.6 GB available	≈ 217K tokensmax 256K
Qwen/Qwen2.5-Coder-7B-Instruct-AWQDense	7.62B	As published5.57 GB of 21.6 GB available	Full 32K
deepseek-ai/DeepSeek-Coder-V2-Lite-InstructMoE	15.7B2.45B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 160K
unsloth/Qwen3.5-4B-GGUFDense	4.21B	BF168.42 GB of 21.6 GB available	Full 256K
CMSManhattan/JiRackUltra_1bDense	1.78B1.54B active	As published3.55 GB of 21.6 GB available	Full 128K
Bahushruth/Qwen3.6-35B-A3B-abliterated-v4MoE	34.7B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 194K tokensmax 256K
Qwen/Qwen2.5-1.5BDense	1.54B	As published3.09 GB of 21.6 GB available	Full 128K
bartowski/XYZAILab_XYZ-Aquila-mini-GGUFMoE	34.7B2.95B active	Q4_K_S20.6 GB of 21.6 GB available	≈ 90K tokensmax 256K
agentionai/Qwen3.8-27B-AP-GGUFDense	27.3B	Q4_K_XL17.6 GB of 21.6 GB available	≈ 116K tokensmax 256K
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTPMoE	35.5B2.95B active	UD-IQ4_XS18.1 GB of 21.6 GB available	Full 256K
deepseek-ai/DeepSeek-R1-0528-Qwen3-8BDense	8.19B	As published16.4 GB of 21.6 GB available	≈ 69K tokensmax 128K
peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUFDense	4.11B	Q6_K_XL3.61 GB of 21.6 GB available	≈ 952K tokensmax 1M
raxcore-dev/Rax-4.5Dense + vision	2.27B1.94B active	As published4.55 GB of 21.6 GB available	Full 256K
unsloth/gemma-4-12b-it-GGUFDense	11.9B	UD-Q8_K_XL13.6 GB of 21.6 GB available	≈ 114K tokensmax 256K
Qwen/Qwen2-VL-7B-InstructDense + vision	8.29B7.07B active	As published16.6 GB of 21.6 GB available	Full 32K
DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUFMoE	24.0B2.45B active	Q6_K20.0 GB of 21.6 GB available	Full 128K
migtissera/Tess-4.5-27B-GGUFDense	26.9B	Q4_K_M16.5 GB of 21.6 GB available	≈ 146K tokensmax 256K
cyankiwi/gemma-4-26B-A4B-it-AWQ-4bitMoE + vision	25.8B	As published17.2 GB of 21.6 GB available	≈ 205K tokensmax 256K
prism-ml/Ternary-Bonsai-2-9B-gguf	1.47B	Ternary-Bonsai-2-9B-PQ2_0-MTP-Q8_02.68 GB of 21.6 GB available	Full 256K
dots-studio/dots.ocrDense + vision	3.04B1.54B active	As published6.08 GB of 21.6 GB available	Full 128K
cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bitMoE	30.5B3.04B active	As published18.1 GB of 21.6 GB available	≈ 70K tokensmax 256K
cyankiwi/Qwen3.8-27B-AWQ-INT4Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-0.6B-BaseDense	596M	As published1.19 GB of 21.6 GB available	Full 32K
empero-ai/Qwen3.8-4B-Distill-GGUFDense	4.33B	BF168.67 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-8B-FP8Dense	8.19B	As published9.44 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-30B-A3B-Instruct-2507MoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 88K tokensmax 256K
unsloth/Qwen3.5-35B-A3B-GGUFMoE	34.7B2.95B active	Q4_K_S20.7 GB of 21.6 GB available	≈ 82K tokensmax 256K
empero-ai/Qwen3.8-2B-Distill-GGUFDense	1.94B	BF163.90 GB of 21.6 GB available	Full 256K
shawnw3i/Huihui-Qwen3.6-27B-abliterated-AWQ-MTPDense + vision	27.8B	As published19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
FINAL-Bench/POCKET-35B-GGUFMoE	34.7B2.95B active	Q4_K_M21.2 GB of 21.6 GB available	≈ 35K tokensmax 256K
Infomaniak-AI/vllm-translategemma-4b-itDense + vision	4.30B	As published8.60 GB of 21.6 GB available	Full 128K
ConwayResearch/Underdog-Saluki-27B-1.0Dense	26.9B	Underdog-Saluki-27B-1.0-IQ2-mix7.90 GB of 21.6 GB available	Full 256K
Qwen/Qwen2-0.5BDense	494M	As published988 MB of 21.6 GB available	Full 128K
LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct-AWQDense	7.82B	As published5.30 GB of 21.6 GB available	Full 32K
Qwen/Qwen2.5-Coder-7BDense	7.62B	As published15.2 GB of 21.6 GB available	Full 32K
meta-models/Muse-Glimmer-30B-GGUFDense	27.9B	Q4_K_XL19.7 GB of 21.6 GB available	Full 128K
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUFDense	11.9B	gemma4-v2-Q8_012.7 GB of 21.6 GB available	≈ 128K tokensmax 256K
Accio-Lab/occamy-1.0-GGUFMoE	34.7B2.95B active	Q4_K_M21.2 GB of 21.6 GB available	≈ 35K tokensmax 256K
OpenGVLab/InternVL2-2B	2.21B	As published4.41 GB of 21.6 GB available	Full 32K
ibm-granite/granite-4.1-30bDense	28.9B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 40K tokensmax 128K
empero-ai/Qwen3.8-9B-Distill-GGUFDense	9.20B7.94B active	BF1618.4 GB of 21.6 GB available	≈ 187K tokensmax 256K
QuantTrio/Qwen3.6-35B-A3B-AWQMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
z-lab/Qwen3.8-27B-DFlash2-GGUF	1.92B	BF163.86 GB of 21.6 GB available	Full 256K
Salesforce/blip2-opt-2.7b	3.74B	As published15.0 GB of 21.6 GB available	≈ 39K tokens
microsoft/Phi-3.5-vision-instructDense + vision	4.15B3.72B active	As published8.29 GB of 21.6 GB available	≈ 66K tokensmax 128K
jegreene/Swift-1.5-Qwen3.8-27B-heretic-GSQ-RCO-GGUFDense	27.3B	IQ3_S12.1 GB of 21.6 GB available	Full 256K
Qwen/Qwen2.5-7BDense	7.62B	As published15.2 GB of 21.6 GB available	Full 128K
google/gemma-4-31BDense + vision	31.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 43K tokensmax 256K
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2Dense	27.3B	Qwen3.8-27B-Coder390-EfficientThink-Q4LynnStyle-Q8MTP19.8 GB of 21.6 GB available	≈ 48K tokensmax 256K
OpenGVLab/InternVL2-1BDense + vision	938M498M active	As published1.88 GB of 21.6 GB available	Full 32K
CMSManhattan/JiRackUltra_14bDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQDense	7.62B	As published5.70 GB of 21.6 GB available	Full 32K
openbmb/MiniCPM5-2B-DSpark	324M	As published648 MB of 21.6 GB available	Full 128K
tencent/HunyuanOCRDense + vision	1.12B950M active	As published2.24 GB of 21.6 GB available	Full 128K
Qwen/Qwen2.5-VL-3B-Instruct-AWQDense + vision	3.75B3.09B active	As published3.40 GB of 21.6 GB available	Full 125K
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUFMoE	34.7B2.95B active	Hermes3.6-35B-A3B-Uncensored-Genesis-MTP-APEX-Compact18.3 GB of 21.6 GB available	Full 256K
farbodtavakkoli/OTel-2.0-LLM-31B-ITDense + vision	31.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 43K tokensmax 256K
OsaurusAI/Diplodocus-preview-GGUFDense	9.00B7.97B active	Q8_09.57 GB of 21.6 GB available	≈ 159K tokensmax 512K
openbmb/MiniCPM-V-4.7-35B-A3BMoE + vision	35.2B2.98B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 165K tokensmax 256K
QuantTrio/gemma-4-31B-it-AWQDense + vision	31.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 43K tokensmax 256K
Qwen/Qwen2.5-3B-Instruct-AWQDense	3.40B	As published2.69 GB of 21.6 GB available	Full 32K
unsloth/Qwen3.6-35B-A3B-NVFP4-FastMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
Qwen/Qwen2.5-7B-Instruct-GGUFDense	7.62B	qwen2.5-7b-instruct-fp1615.2 GB of 21.6 GB available	Full 128K
Lorbus/Qwen3.6-27B-int4-AutoRoundDense + vision	27.8B	As published19.0 GB of 21.6 GB available	≈ 73K tokensmax 256K
Qwen/Qwen2-1.5B-InstructDense	1.54B	As published3.09 GB of 21.6 GB available	Full 32K
unsloth/gemma-4-E2B-it-GGUF	4.65B	BF169.31 GB of 21.6 GB available	Full 128K
mlx-community/Qwen3.8-27B-4bitDense + vision	27.4B	As published16.1 GB of 21.6 GB available	≈ 161K tokensmax 256K
AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUFMoE	24.0B2.45B active	Q6_K20.9 GB of 21.6 GB available	≈ 66K tokensmax 128K
poolside/Laguna-XS-2.1MoE	33.4B2.81B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 131K tokensmax 256K
HuggingFaceTB/SmolLM3-3BDense	3.08B	As published6.15 GB of 21.6 GB available	Full 64K
OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HFMoE + vision	21.2B3.61B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
unsloth/Llama-3.2-1B-InstructDense	1.24B	As published2.47 GB of 21.6 GB available	Full 128K
bartowski/Qwen2.5-32B-Instruct-GGUFDense	32.8B	Q3_K_L17.2 GB of 21.6 GB available	Full 32K
google/diffusiongemma-26B-A4B-itMoE + vision	25.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
dealignai/Ornith-1.5-9B-UNCENSORED-GGUFDense	8.95B7.94B active	Q8_09.53 GB of 21.6 GB available	Full 256K
lmstudio-community/Qwen3.5-9B-MLX-4bitDense + vision	9.41B7.94B active	As published5.95 GB of 21.6 GB available	Full 256K
cyankiwi/MiniCPM-SALA-AWQ-8bitDense	9.48B	As published10.6 GB of 21.6 GB available	Full 512K
unsloth/gemma-4-26B-A4B-it-GGUFMoE	25.2B3.82B active	UD-Q5_K_S18.9 GB of 21.6 GB available	≈ 61K tokensmax 256K
ibm-granite/granite-4.1-3bDense	3.40B	As published6.81 GB of 21.6 GB available	Full 128K
unsloth/gemma-4-E4B-it-GGUF	7.52B	BF1615.1 GB of 21.6 GB available	Full 128K
poolside/Laguna-XS.2MoE	33.4B2.81B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 131K tokensmax 256K
PrimeIntellect/Qwen3-0.6BDense	752M596M active	As published1.50 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-14B-BaseDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 32K
lmstudio-community/Qwen3.5-9B-MLX-8bitDense + vision	9.41B7.94B active	As published10.4 GB of 21.6 GB available	Full 256K
HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-BalancedDense	11.9B	Q4_K_M7.38 GB of 21.6 GB available	≈ 207K tokensmax 256K
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUFMoE	34.7B2.95B active	Hermes3.6-35B-A3B-Uncensored-Genesis-Final-MTP-APEX-Compact18.3 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-Coder-30B-A3B-InstructMoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 88K tokensmax 256K
empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUFDense	9.20B7.94B active	Qwythos-9B-Claude-Mythos-5-1M-MTP-BF1618.4 GB of 21.6 GB available	≈ 187K tokensmax 1M
ornith-ai/Ornith-1.5-9BDense + vision	9.65B8.18B active	As published19.3 GB of 21.6 GB available	≈ 134K tokensmax 256K
Qwen/Qwen3.5-4B-BaseDense + vision	4.66B	As published9.32 GB of 21.6 GB available	Full 256K
XHToken/Spark-X2.6-4B-GGUFDense	4.45B	Spark-X2.6-4B8.23 GB of 21.6 GB available	≈ 707K tokensmax 1M
Qwen/Qwen3-30B-A3B-Instruct-2507-FP8MoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 88K tokensmax 256K
Qwen/Qwen3-VL-30B-A3B-InstructMoE + vision	31.1B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 82K tokensmax 256K
Qwen/Qwen3-8B-BaseDense	8.19B	As published16.4 GB of 21.6 GB available	Full 32K
peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUFMoE	34.7B2.95B active	UD-Q4_K_S20.9 GB of 21.6 GB available	≈ 61K tokensmax 256K
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUFDense	27.3B	Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-Q5_K_S20.2 GB of 21.6 GB available	≈ 38K tokensmax 256K
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5BDense	1.78B1.54B active	As published3.55 GB of 21.6 GB available	Full 128K
Qwen/Qwen3-4B-GGUFDense	4.02B	Q8_04.28 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-4B-Thinking-2507Dense	4.02B	As published8.04 GB of 21.6 GB available	≈ 180K tokensmax 256K
Qwen/Qwen3.5-35B-A3B-GPTQ-Int4MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
ornith-ai/Ornith-1.5-35B-A3BMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
Qwen/Qwen3-8B-GGUFDense	8.19B	Q8_08.71 GB of 21.6 GB available	Full 40K
Qwen/Qwen3.5-9B-BaseDense + vision	9.65B8.18B active	As published19.3 GB of 21.6 GB available	≈ 134K tokensmax 256K
Qwen/Qwen3-VL-4B-Instruct-FP8Dense + vision	4.83B4.02B active	As published6.02 GB of 21.6 GB available	≈ 206K tokensmax 256K
mistralai/Mistral-7B-v0.1Dense	7.24B	As published14.5 GB of 21.6 GB available	Full 32K
HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTPMoE	25.2B3.82B active	Q4_K_M16.8 GB of 21.6 GB available	≈ 110K tokensmax 256K
Qwen/Qwen3.5-2B-BaseDense + vision	2.27B1.94B active	As published4.55 GB of 21.6 GB available	Full 256K
deepseek-ai/DeepSeek-R1-Distill-Qwen-14BDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
bottlecapai/ThinkingCap-Qwen3.8-27B-GGUFDense	27.3B	Q4_K_M17.4 GB of 21.6 GB available	≈ 119K tokensmax 256K
Qwen/Qwen2.5-3BDense	3.09B	As published6.17 GB of 21.6 GB available	Full 32K
Qwen/Qwen2.5-Coder-7B-Instruct-GGUFDense	7.62B	Q8_08.10 GB of 21.6 GB available	Full 128K
AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUFMoE	34.7B2.95B active	IQ4_XS20.1 GB of 21.6 GB available	≈ 135K tokensmax 256K
ukisai/Swift-Qwen3.8-27B-GGUFDense	27.3B	Q5_K_M20.2 GB of 21.6 GB available	≈ 37K tokensmax 256K
deepseek-ai/DeepSeek-R1-Distill-Qwen-7BDense	7.62B	As published15.2 GB of 21.6 GB available	Full 128K
bartowski/Qwen3.8-27B-GGUFDense	27.3B	Q5_K_S19.6 GB of 21.6 GB available	≈ 56K tokensmax 256K
Qwen/Qwen3-0.6B-FP8Dense	752M596M active	As published1.06 GB of 21.6 GB available	Full 40K
Qwen/Qwen3.5-0.8B-BaseDense + vision	873M773M active	As published1.75 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-4B-AWQDense	4.02B	As published2.67 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-VL-30B-A3B-Instruct-FP8MoE + vision	31.1B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 82K tokensmax 256K
XHToken/Spark-X2.5-4B-GGUFDense	4.11B	Spark-X2.5-4B8.23 GB of 21.6 GB available	≈ 707K tokensmax 1M
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUFDense	11.9B	Q8_012.7 GB of 21.6 GB available	≈ 128K tokensmax 256K
openbmb/MiniCPM-V-4.7-35B-A3B-ggufMoE	34.7B2.95B active	Q4_K_M21.2 GB of 21.6 GB available	≈ 35K tokensmax 256K
Qwen/Qwen3-0.6B-GGUFDense	596M	Q8_0639 MB of 21.6 GB available	Full 40K
Qwen/Qwen3-14B-GGUFDense	14.8B	Q8_015.7 GB of 21.6 GB available	Full 40K
meta-models/Muse-Glimmer-30BDense + vision	29.8B26.5B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
deepseek-ai/DeepSeek-R1-Distill-Llama-8BDense	8.03B	As published16.1 GB of 21.6 GB available	≈ 83K tokensmax 128K
Qwen/Qwen3.5-27B-FP8Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-30B-A3B-FP8MoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
moonshotai/Kimi-VL-A3B-InstructMoE + vision	16.4B2.58B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
LiquidAI/LFM3-1.7B-GGUF	1.73B	BF163.47 GB of 21.6 GB available	Full 256K
openbmb/MiniCPM-V-4.6Dense + vision	1.30B778M active	As published2.60 GB of 21.6 GB available	Full 256K
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUFDense	27.3B	Qwen3.8-27B-TTURBO-Fable-C-Fusion-709-L-Uncen-NM-DAU-NEO-MTP-Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUFMoE	12.1B2.21B active	Mellum2.1-12B-A2.5B-Thinking-MTP-Q8_013.4 GB of 21.6 GB available	Full 128K
Qwen/Qwen3-30B-A3B-GPTQ-Int4MoE	30.5B3.04B active	As published16.9 GB of 21.6 GB available	Full 40K
openbmb/MiniCPM5-2B-GGUFDense	2.52B2.25B active	F165.04 GB of 21.6 GB available	Full 128K
Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUFDense	9.20B7.94B active	Q8_09.79 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-VL-8B-ThinkingDense + vision	8.77B7.57B active	As published17.5 GB of 21.6 GB available	≈ 54K tokensmax 256K
ReliquaryForge/qwen3-4b-base-dapo-v4Dense	4.02B	As published8.04 GB of 21.6 GB available	Full 32K
baidu/Unlimited-OCR-2MoE + vision	3.34B680M active	As published6.69 GB of 21.6 GB available	Full 128K
Qwen/Qwen3Guard-Gen-0.6BDense	752M596M active	As published1.50 GB of 21.6 GB available	Full 32K
Qwen/Qwen3-VL-8B-Instruct-GGUFDense	8.19B	F1616.4 GB of 21.6 GB available	≈ 69K tokensmax 256K
Qwen/Qwen3-VL-4B-Instruct-GGUFDense	4.02B	F168.05 GB of 21.6 GB available	≈ 179K tokensmax 256K
Qwen/Qwen3.5-35B-A3B-BaseMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInferDense	27.3B	Qwen3.8-27B-Coder390-EfficientThink-Q4LynnStyle-Q8MTP19.8 GB of 21.6 GB available	≈ 48K tokensmax 256K
Qwen/Qwen3-14B-FP8Dense	14.8B	As published16.3 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-VL-2B-Instruct-GGUFDense	1.72B	F163.45 GB of 21.6 GB available	Full 256K
LiquidAI/LFM2.5-2.6B	2.70B	As published5.39 GB of 21.6 GB available	Full 128K
cyankiwi/Qwen3-VL-8B-Instruct-AWQ-4bitDense + vision	8.77B7.57B active	As published7.55 GB of 21.6 GB available	≈ 186K tokensmax 256K
Qwen/Qwen3-VL-2B-ThinkingDense + vision	2.13B1.72B active	As published4.26 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-VL-2B-Instruct-FP8Dense + vision	2.44B1.72B active	As published3.47 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-4B-FP8Dense	4.41B	As published5.19 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-30B-A3B-Thinking-2507MoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 88K tokensmax 256K
bartowski/Nanbeige_Nanbeige4.3-33B-GGUFDense	33.1B	IQ3_M17.8 GB of 21.6 GB available	≈ 35K tokensmax 512K
nvidia/LocateAnything-3BDense + vision	3.83B3.10B active	As published7.66 GB of 21.6 GB available	Full 32K
ukisai/Swift-1.5-Qwen3.8-27B-GGUFDense	27.3B	Q5_K_S19.6 GB of 21.6 GB available	≈ 56K tokensmax 256K
Qwen/Qwen3-30B-A3B-BaseMoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 32K
Qwen/Qwen2.5-14BDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
Edge0/Edge0-35B-A3B-previewMoE	34.7B2.95B active	As published19.5 GB of 21.6 GB available	≈ 193K tokensmax 256K
LiquidAI/LFM3-1.7B	1.73B	As published3.46 GB of 21.6 GB available	Full 256K
huihui-ai/Huihui-Qwen3.8-27B-abliteratedDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-1.7B-GGUFDense	1.72B	Q8_01.83 GB of 21.6 GB available	Full 40K
LiquidAI/LFM3-VL-2B-GGUF	1.73B	BF163.47 GB of 21.6 GB available	Full 125K
Qwen/Qwen3-30B-A3B-GGUFMoE	30.5B3.04B active	Q4_K_M18.6 GB of 21.6 GB available	Full 40K
LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUFDense	26.9B	Q5_K_M19.2 GB of 21.6 GB available	≈ 66K tokensmax 256K
jialinyyzz/humanizerDense + vision	12.0B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
Qwen/Qwen3Guard-Gen-4BDense	4.41B	As published8.82 GB of 21.6 GB available	Full 32K
Qwen/Qwen3-VL-4B-ThinkingDense + vision	4.44B	As published8.88 GB of 21.6 GB available	≈ 169K tokensmax 256K
Qwen/Qwen3.5-27B-GPTQ-Int4Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
orcarouter/Qwen3.8-27B-Uncensored-MLXDense + vision	27.4B	As published16.1 GB of 21.6 GB available	≈ 161K tokensmax 256K
openbmb/MiniCPM-V-4.7-1B-ggufDense	1.01B752M active	F162.02 GB of 21.6 GB available	Full 256K
google/gemma-4-26B-A4BMoE + vision	25.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
unsloth/LFM2.5-24B-A2B-GGUFMoE	24.0B2.45B active	UD-Q5_K_XL17.9 GB of 21.6 GB available	Full 128K
XingChen-AGI/TeleOCRDense + vision	1.42B596M active	As published2.83 GB of 21.6 GB available	Full 125K
RavichandranJ/Dolphin3-Cyber-8B-GGUFDense	8.03B	F1616.1 GB of 21.6 GB available	≈ 82K tokensmax 128K
DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF	2.70B	BF165.40 GB of 21.6 GB available	Full 128K
Qwen/Qwen3-VL-30B-A3B-Instruct-GGUFMoE	30.5B3.04B active	Q4_K_M18.6 GB of 21.6 GB available	≈ 60K tokensmax 256K
Qwen/Qwen3Guard-Gen-8BDense	8.19B	As published16.4 GB of 21.6 GB available	Full 32K
ggml-org/Clef-Flash-GGUFDense	9.08B8.06B active	BF1618.2 GB of 21.6 GB available	≈ 202K tokensmax 256K
PaddlePaddle/PaddleOCR-VL-1.6Dense + vision	959M387M active	As published1.92 GB of 21.6 GB available	Full 128K
Cloudflare/clefDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
Cloudflare/clef-flashDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUFMoE	34.7B2.95B active	UD-Q4_K_S20.9 GB of 21.6 GB available	≈ 61K tokensmax 256K
openbmb/MiniCPM-V-4.7-1BDense + vision	1.55B778M active	As published3.11 GB of 21.6 GB available	Full 256K
EldanRing/Winnow-12BDense	11.9B	Q8_012.7 GB of 21.6 GB available	≈ 128K tokensmax 256K
IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUFMoE	34.7B2.95B active	Qwen3.8-35B-A3B-Distill.APEX-I-MiniPlus-V2.1-Abliterated14.7 GB of 21.6 GB available	Full 256K
StarDoc-AI/TeleOCRDense + vision	1.42B596M active	As published2.83 GB of 21.6 GB available	Full 125K
XHToken/Spark-X2.5-4B	4.11B	As published8.22 GB of 21.6 GB available	≈ 707K tokensmax 1M
DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUFDense	27.3B	Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
IFM/K2-Horizon-7BDense	9.00B7.97B active	As published18.0 GB of 21.6 GB available	≈ 48K tokensmax 512K
cyjin-yl/Qwen3.8-27B-Uncensored-Cyber-agentic-imatrix-GGUFDense	27.3B	IQ4_XS16.5 GB of 21.6 GB available	≈ 147K tokensmax 256K
empero-ai/Qwen3.8-35B-A3B-Distill-GGUFMoE	35.5B2.95B active	IQ4_XS19.6 GB of 21.6 GB available	≈ 182K tokensmax 256K
moonshotai/Kimi-VL-A3B-Thinking-2506MoE + vision	16.4B2.58B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
byteshape/Qwen3.8-27B-GGUFDense	27.3B	IQ4_XS13.1 GB of 21.6 GB available	≈ 249K tokensmax 256K
Qwen/Qwen3-VL-8B-Thinking-FP8Dense + vision	8.77B7.57B active	As published10.6 GB of 21.6 GB available	≈ 146K tokensmax 256K
bartowski/Cloudflare_clef-GGUFDense	27.0B	Q5_K_S19.6 GB of 21.6 GB available	≈ 56K tokensmax 256K
Jackrong/Qwopus3.8-27B-Coder-Flash-GGUFDense	27.3B	Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
TokenRhythm/NeoHorse-1-4BDense	4.21B	As published8.41 GB of 21.6 GB available	Full 256K
RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-UncensoredDense	27.3B	Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-v2.010.5 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-30B-A3B-Thinking-2507-FP8MoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 88K tokensmax 256K
bartowski/ukisai_Swift-Qwen3.8-27b-GGUFDense	27.3B	Q5_K_S19.6 GB of 21.6 GB available	≈ 56K tokensmax 256K
TokenRhythm/NeoHorse-1-4B-GGUFDense	4.21B	BF168.42 GB of 21.6 GB available	Full 256K
IFM/K2-Horizon-7B-GGUFDense	9.00B7.97B active	BF1618.0 GB of 21.6 GB available	≈ 48K tokensmax 512K
webAI-Official/TwIL-8BDense	8.79B	As published17.6 GB of 21.6 GB available	≈ 48K tokensmax 128K
Qwen/Qwen3-1.7B-FP8Dense	2.03B1.72B active	As published2.65 GB of 21.6 GB available	Full 40K
IFM/K2-Horizon-3.7BDense	5.06B4.42B active	As published10.1 GB of 21.6 GB available	≈ 152K tokensmax 512K
AtomicChat/Nanbeige4.3-33B-GGUFDense	33.1B	IQ3_S17.1 GB of 21.6 GB available	≈ 42K tokensmax 512K
XHToken/Spark-X2.6-4B	4.11B	As published8.22 GB of 21.6 GB available	≈ 707K tokensmax 1M
Diffuspace/Clover-35B-A3B-Preview-GGUFMoE	34.7B2.95B active	Q4_019.6 GB of 21.6 GB available	Full 128K
Qwen/Qwen3-VL-2B-Thinking-FP8Dense + vision	2.44B1.72B active	As published3.47 GB of 21.6 GB available	Full 256K
bartowski/FrogNano-4B-2609-GGUFDense	4.33B	BF168.67 GB of 21.6 GB available	Full 256K
deepgrove/maple-preview-GGUFMoE	20.2B1.18B active	maple-preview-TQ2_0-head-F166.35 GB of 21.6 GB available	Full 128K
LiquidAI/d1-2B-GGUF	1.73B	BF163.47 GB of 21.6 GB available	Full 125K
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9BDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
openbmb/MiniCPM-OCR-1.0Dense + vision	1.30B778M active	As published2.60 GB of 21.6 GB available	Full 256K
ukisai/Swift-Qwen3.8-27bDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-NM-DAU-NEO-MTP-GGUFDense	27.3B	Q4_K_M18.5 GB of 21.6 GB available	≈ 88K tokensmax 256K
agentionai/Signal-3.8-27B-GGUFDense	27.3B	Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
webAI-Official/Air-26B-A4B-ggufMoE	25.2B3.82B active	Air-26B-A4B13.5 GB of 21.6 GB available	≈ 189K tokensmax 256K
JetBrains/Qwen3.8-3.6-27B-blend-GGUFDense	27.3B	Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
paradigma-inc/limite-1b-violettoDense	1.04B	As published2.07 GB of 21.6 GB available	Full 128K
moonshotai/Kimi-VL-A3B-ThinkingMoE + vision	16.4B2.58B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
xiaomi-research/Xiaomi-OCR-0Dense + vision	873M773M active	As published1.75 GB of 21.6 GB available	Full 256K
LiquidAI/LFM2.5-24B-A2BMoE	24.0B2.45B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUFDense	27.3B	IQ3_S12.2 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-VL-30B-A3B-ThinkingMoE + vision	31.1B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 82K tokensmax 256K
Qwen/Qwen3-VL-30B-A3B-Thinking-GGUFMoE	30.5B3.04B active	Q4_K_M18.6 GB of 21.6 GB available	≈ 60K tokensmax 256K
SC117/Spark-X2.6-4B-abliterated-FIT-GGUFDense	4.11B	BF168.23 GB of 21.6 GB available	≈ 707K tokensmax 1M
IFM/K2-Horizon-0.9BDense	1.08B	As published2.16 GB of 21.6 GB available	Full 128K
bartowski/Cloudflare_clef-flash-GGUFDense	9.08B8.06B active	BF1618.2 GB of 21.6 GB available	≈ 202K tokensmax 256K
AtomicChat/Ripple-65B-Preview-GGUFDense	64.8B	IQ2_XXS20.0 GB of 21.6 GB availableunder 3 bits: noticeably lower quality	≈ 43K tokensmax 2M
HemmingwayAI/Hemmingway-1Dense	27.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
deepseek-ai/DeepSeek-Coder-V2-Lite-BaseMoE	15.7B2.45B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 160K
Qwen/Qwen3-VL-30B-A3B-Thinking-FP8MoE + vision	31.1B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 82K tokensmax 256K
ccore/Qwen3.5-4B-GLB-3D-CoderDense + vision	4.54B	As published17.5 GB of 21.6 GB available	≈ 242K tokensmax 256K
TokenRhythm/NeoHorse-1-9BDense	8.95B7.94B active	As published17.9 GB of 21.6 GB available	≈ 217K tokensmax 256K
LiquidAI/LFM3-VL-2B	1.92B	As published3.84 GB of 21.6 GB available	Full 125K
tencent/Hy-Memory-30B-A3B-GGUFMoE	30.1B3.20B active	Q4_K_M18.2 GB of 21.6 GB available	≈ 67K tokensmax 256K
Alissonerdx/Molmo2-8B-Minimax-H3Dense + vision	16.7B	As published9.29 GB of 21.6 GB available	Full 36K
unsloth/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUFMoE	74.0B8.56B active	UD-IQ1_M20.3 GB of 21.6 GB availableunder 3 bits: noticeably lower quality	Full 256K
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAUDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16	3.98B	As published7.95 GB of 21.6 GB available	≈ 144K tokensmax 256K
openbmb/MiniCPM-OCR-1.0-ggufDense	752M	F161.52 GB of 21.6 GB available	Full 256K
Altworld/Hemmingway-1Dense	27.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUFDense	33.1B	IQ3_M16.1 GB of 21.6 GB available	≈ 50K tokensmax 512K
Kujira/Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUFDense	27.3B	Underdog-Saluki-27B-1.0-IQ2-mix-MTP-abliterated8.35 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-4B-Thinking-2507-FP8Dense	4.41B	As published5.19 GB of 21.6 GB available	≈ 217K tokensmax 256K
peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUFDense	2.52B2.25B active	Q8_K_M2.93 GB of 21.6 GB available	Full 128K
nex-agi/Nex-N2.5-miniMoE + vision	35.1B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 170K tokensmax 256K
bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUFDense	8.95B7.94B active	BF1617.9 GB of 21.6 GB available	≈ 216K tokensmax 256K
DavidAU/LFM2.5-8B-A1B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUFMoE	8.47B1.69B active	BF1616.9 GB of 21.6 GB available	Full 125K
GrootTeam/Groot-19B-A3B-261023-GGUFMoE	19.0B2.94B active	Q4_K_M11.7 GB of 21.6 GB available	Full 256K
XHToken/Spark-X2.6-1.7B-GGUFDense	1.98B1.71B active	Spark-X2.6-1.7B3.42 GB of 21.6 GB available	Full 1M
XingChen-AGI/Xing4.0-29B-A4BMoE	31.2B3.93B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 171K tokensmax 256K
AtomicChat/LFM3-1.7B-GGUF	1.73B	Q8_01.85 GB of 21.6 GB available	Full 256K
Kujira/Underdog-Saluki-27B-1.0-MTP-GGUFDense	27.3B	Underdog-Saluki-27B-1.0-IQ2-mix-MTP8.35 GB of 21.6 GB available	Full 256K
xtools-at/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-hereticDense + vision	4.66B	As published9.32 GB of 21.6 GB available	Full 256K
ggml-org/Clef-GGUFDense	27.0B	Q4_K_M19.2 GB of 21.6 GB available	≈ 66K tokensmax 256K
LiquidAI/d1-2B	1.92B	As published3.84 GB of 21.6 GB available	Full 125K
higa2515/Qwen3.8-27B-QSA-GGUFDense	27.4B	UD-Q5_K_M20.0 GB of 21.6 GB available	≈ 44K tokensmax 256K
h2oai/h2o-lightning-4bDense + vision	4.66B	As published9.32 GB of 21.6 GB available	Full 256K
LiquidAI/LFM2.5-24B-A2B-MLX-4bitMoE	24.0B2.45B active	As published13.6 GB of 21.6 GB available	Full 128K
medismera/Qwen3.8-27B-OBLITERATED-Mythos-Class-AgenticDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
DeepHat/DeepHat-V1-7BDense	7.62B	As published15.2 GB of 21.6 GB available	Full 32K
bartowski/NousResearch_Arete-27B-GGUFDense	26.9B	Q5_K_S19.3 GB of 21.6 GB available	≈ 63K tokensmax 256K
saidutta69/Qwen3.5-4B-hereticDense + vision	4.54B	As published9.08 GB of 21.6 GB available	Full 256K
LiquidAI/LFM3-1.7B-Base	1.73B	As published3.46 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-VL-8B-Thinking-GGUFDense	8.19B	F1616.4 GB of 21.6 GB available	≈ 69K tokensmax 256K
ATH-MaaS/OvisOCR3Dense + vision	853M752M active	As published1.71 GB of 21.6 GB available	Full 256K
saidutta69/MiniCPM-V-4.7-1B-hereticDense + vision	1.55B778M active	As published3.11 GB of 21.6 GB available	Full 256K
Qwen/Qwen2-VL-2BDense + vision	2.21B1.54B active	As published4.42 GB of 21.6 GB available	Full 32K
bartowski/Altworld_Hemmingway-1-GGUFDense	27.3B	Q5_K_S19.6 GB of 21.6 GB available	≈ 56K tokensmax 256K
ggml-org/OpenJev-GGUFDense	26.9B	Q4_K_M19.0 GB of 21.6 GB available	≈ 74K tokensmax 256K
SeerRay-Lab/Xiaomi-OCR-0Dense + vision	873M773M active	As published1.75 GB of 21.6 GB available	Full 256K
Qwen/Qwen2.5-Coder-14BDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 32K
openbmb/MiniCPM-SALADense	9.48B	As published19.0 GB of 21.6 GB available	≈ 158K tokensmax 512K
XingChen-AGI/Xing4.0-29B-A4B-GGUFMoE	31.2B3.93B active	IQ4_NL20.1 GB of 21.6 GB available	≈ 63K tokensmax 256K
tencent/WeVisOne-VL-2BDense + vision	2.44B1.72B active	As published4.88 GB of 21.6 GB available	Full 256K
webAI-Official/TwIL-LM3-ProDense	3.66B	As published7.32 GB of 21.6 GB available	Full 128K
Jackrong/Qwopus3-5-9B-Coder-Flash-GGUFDense	9.20B7.94B active	BF1618.4 GB of 21.6 GB available	≈ 187K tokensmax 256K
TaichuAI/ZDTaichu5.0-9BDense + vision	9.79B8.13B active	As published19.6 GB of 21.6 GB available	≈ 117K tokensmax 256K
Qwen/Qwen3-VL-4B-Thinking-GGUFDense	4.02B	F168.05 GB of 21.6 GB available	≈ 179K tokensmax 256K
ukisai/Swift-1.5-Qwen3.8-27bDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
tencent/Youtu-Parsing-OmniDense + vision	5.33B	As published10.7 GB of 21.6 GB available	≈ 463K tokensmax 1M
empero-ai/Qwen3.8-35B-A3B-DistillMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
internlm/Intern-Decision-0.8BDense + vision	853M752M active	As published1.71 GB of 21.6 GB available	Full 256K
zgcagi/ZGCM-1-7BDense	7.39B	As published14.8 GB of 21.6 GB available	Full 256K
basecompute/Qwen3.8-27B-BaseQuant-V1Dense	26.9B	Qwen3.8-27B-BaseQuant-V1-Medium16.4 GB of 21.6 GB available	≈ 150K tokensmax 256K
Hikari07jp/MiMo-V2.6-Distill-Qwen-9B-AblitratedDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
jialinyyzz/humanizer-GGUFDense	11.9B	Q8_012.7 GB of 21.6 GB available	≈ 128K tokensmax 256K
XHToken/Spark-X2.6-1.7B	1.71B	As published3.42 GB of 21.6 GB available	Full 1M
empero-ai/Qwen3.8-2B-DistillDense + vision	2.27B1.94B active	As published4.55 GB of 21.6 GB available	Full 256K
XingChen-AGI/Xing4.0-29B-IntentMoE	31.2B3.93B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 171K tokensmax 256K
endless-frontier/BigBang-v1MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
bytkim/Qwen3.8-27B-pi-GGUFDense	26.9B	Q5_K_M19.2 GB of 21.6 GB available	≈ 66K tokensmax 256K
HuggingFaceBio/Carbon-XDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
fastino/GLiDE-27BDense + vision	26.1B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 202K tokensmax 256K
tsinghua-sigs-robot-lab/VeriLoop-E2Dense + vision	27.9B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 172K tokensmax 256K
openbmb/MiniCPM-V-4.7-35B-A3B-DSpark	389M	As published778 MB of 21.6 GB available	Full 256K
tencent/WeVisOne-VL-4BDense + vision	4.83B4.02B active	As published9.66 GB of 21.6 GB available	≈ 158K tokensmax 256K
OrionLLM/OxCoder-9BDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
Accio-Lab/occamy-1.0MoE + vision	35.1B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 170K tokensmax 256K
deepgrove/maple-previewMoE	20.2B1.18B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
taobao-mnn/MNN-Pocket-0.3BDense	362M303M active	As published723 MB of 21.6 GB available	Full 40K
thesysdev/OUI-1MoE + vision	25.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
juspay/xorMoE + vision	35.1B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 170K tokensmax 256K
ttindall/Qwen3.8-27B-Defiance-Uncensored-MTP-GGUFDense	27.3B	IQ4_XS15.7 GB of 21.6 GB available	≈ 171K tokensmax 256K
AtomicChat/LFM3-1.7B-Uncensored-GGUF	1.73B	Q6_K1.59 GB of 21.6 GB available	Full 256K
Abiray/Hemmingway-1-heretic-GGUFDense	27.3B	Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-UncensoredDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUFDense	8.95B7.94B active	Q8_09.53 GB of 21.6 GB available	Full 256K
openbmb/MiniCPM-OCR-JevDense + vision	2.21B1.88B active	As published4.43 GB of 21.6 GB available	Full 256K
XHToken/Spark-X2.6-4B-Base	4.11B	As published8.22 GB of 21.6 GB available	≈ 707K tokensmax 1M
terrorswift/REDCELL-26B-A4B-OSINT-Cyber-APEX-GGUFMoE	25.2B3.82B active	REDCELL-26B-A4B-OSINT-Cyber-APEX-I-Quality19.7 GB of 21.6 GB available	≈ 40K tokensmax 256K
aj9o9/Qwen3.8-27B-DSpine-b16-GGUF	2.03B	BF164.06 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-14B-MLX-4bitDense	14.8B	As published7.85 GB of 21.6 GB available	Full 40K
emperorofrome/GmcoderDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
XHToken/Spark-X2.6-4B-DSpark-GGUF	624M	Spark-X2.6-4B-DSpark1.25 GB of 21.6 GB available	Full 1M
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTPDense + vision	9.65B8.18B active	As published19.3 GB of 21.6 GB available	≈ 134K tokensmax 256K
XHToken/Spark-X2.6-4B-FP8	4.11B	As published4.45 GB of 21.6 GB available	≈ 907K tokensmax 1M
HemmingwayAI/Hemmingway-1.5Dense	27.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
Qwen/Qwen3-8B-MLX-4bitDense	8.19B	As published4.35 GB of 21.6 GB available	Full 40K
summerAIO/Diffusion-Qwen3.8-27BDense	26.9B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 188K tokensmax 256K
Qwen/Qwen3-VL-2B-Thinking-GGUFDense	1.72B	F163.45 GB of 21.6 GB available	Full 256K
togethercomputer/Tev1-4B-experimentalDense + vision	4.66B	As published9.32 GB of 21.6 GB available	Full 256K
divagr1925/Qwen3.5-4B-QwenputerDense	9.36B	As published18.7 GB of 21.6 GB available	≈ 167K tokensmax 256K
sensenova/SenseNova-Loop-9B-PreviewDense + vision	9.66B8.18B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
tencent/Qwen3.8-27B-DSpine-b16	2.03B	As published4.05 GB of 21.6 GB available	Full 256K
jinaai/jina-ocr-v1MoE + vision	3.37B708M active	As published6.74 GB of 21.6 GB available	Full 32K
XHToken/Spark-X2.5-4B-Base	4.11B	As published8.22 GB of 21.6 GB available	≈ 707K tokensmax 1M
Qwen/Qwen3-4B-MLX-4bitDense	4.02B	As published2.14 GB of 21.6 GB available	Full 64K
dealignai/Nanbeige4.3-33B-UNCENSORED-GGUFDense	33.1B	IQ2_XXS9.33 GB of 21.6 GB availableunder 3 bits: noticeably lower quality	≈ 113K tokensmax 512K
xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-hereticDense + vision	9.65B8.18B active	As published19.3 GB of 21.6 GB available	≈ 134K tokensmax 256K
LiquidAI/LFM2.5-24B-A2B-FP8MoE	24.0B2.45B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
Hcompany/Holo4-27B-GGUFDense	26.9B	Q4_K_M16.9 GB of 21.6 GB available	≈ 136K tokensmax 256K
Qwen/Qwen3-0.6B-MLX-4bitDense	596M	As published317 MB of 21.6 GB available	Full 38K
datalab-to/surya-ocr-2.5Dense + vision	689M589M active	As published1.38 GB of 21.6 GB available	Full 256K
Jackrong/Qwopus3.8-27B-Coder-FlashDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen2-VL-7BDense + vision	8.29B7.07B active	As published16.6 GB of 21.6 GB available	Full 32K
Qwen/WebWorld-8BDense	8.19B	As published16.4 GB of 21.6 GB available	Full 40K
bottlecapai/ThinkingCap-Qwen3.8-27B-NVFP4Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-4B-SafeRLDense	4.02B	As published8.04 GB of 21.6 GB available	Full 40K
XHToken/Spark-X2.6-1.7B-Base	1.71B	As published3.42 GB of 21.6 GB available	Full 1M
JetBrains/Qwen3.8-3.6-27B-blendDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Jackrong/DeepSeek-V4-Pro-Qwen3.5-9BDense + vision	9.65B8.18B active	As published19.3 GB of 21.6 GB available	≈ 134K tokensmax 256K
IFM/K2-Type-0.9BDense	1.08B	As published2.16 GB of 21.6 GB available	Full 128K
Octen/Octen-WebGR-0.6BDense	730M	As published1.46 GB of 21.6 GB available	Full 32K
lukey03/Qwen3.5-9B-abliteratedDense	8.95B7.94B active	As published17.9 GB of 21.6 GB available	≈ 217K tokensmax 256K
microsoft/Sentiment-Analysis-7BDense	7.24B	As published14.5 GB of 21.6 GB available	Full 32K
Octen/Octen-WebGR-4BDense	4.36B	As published8.72 GB of 21.6 GB available	Full 32K
Remek/basal-omni-1.0-ultraDense + vision	31.3B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 43K tokensmax 256K
p-e-w/Oc-e-Non-v1Dense	4.02B	As published8.04 GB of 21.6 GB available	≈ 180K tokensmax 256K
GroundingPI/GroundAnything-VLMDense + vision	4.84B4.02B active	As published9.69 GB of 21.6 GB available	≈ 158K tokensmax 256K
Qwen/Qwen3-VL-4B-Thinking-FP8Dense + vision	4.83B4.02B active	As published6.02 GB of 21.6 GB available	≈ 206K tokensmax 256K
google/DiarizationLM-Gemma-4-E4B-v1Dense + vision	8.00B	As published16.0 GB of 21.6 GB available	Full 128K
allenai/AstaBrief_8BDense	8.19B	As published16.4 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-1.7B-MLX-4bitDense	1.72B	As published914 MB of 21.6 GB available	Full 64K
mlabonne/LFM2.5-230M-Chess	231M	As published461 MB of 21.6 GB available	Full 125K
Qwen/WebWorld-14BDense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
Qwen/Qwen3-0.6B-GPTQ-Int8Dense	596M	As published763 MB of 21.6 GB available	Full 40K
LiquidAI/d1-omni-600M-GGUF	381M	BF16764 MB of 21.6 GB available	Full 125K
abacusai/Smaug-HumanizerDense + vision	12.0B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
Mapika/decider-2b-visionDense + vision	2.21B1.88B active	As published4.43 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-1.7B-GPTQ-Int8Dense	1.72B	As published2.07 GB of 21.6 GB available	Full 40K
sensenova/SenseNova-6.8-Code2VideoDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
sabicap/sabi-noemaDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
Qwen/Qwen3-8B-MLX-8bitDense	8.19B	As published8.45 GB of 21.6 GB available	Full 40K
amazon/ALoDLM-8BDense	8.19B	As published16.4 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-14B-MLX-6bitDense	14.8B	As published11.5 GB of 21.6 GB available	Full 40K
LiquidAI/LFM2.5-VL-3B-DSpark	279M	As published559 MB of 21.6 GB available	Full 125K
Qwen/Qwen3-30B-A3B-MLX-4bitMoE	30.5B3.04B active	As published16.2 GB of 21.6 GB available	Full 40K
scratchyone/anon-1bDense	1000M	As published2.60 GB of 21.6 GB available	Full 32K
maritaca-ai/S5-nanoDense + vision	4.66B	As published9.32 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-14B-MLX-8bitDense	14.8B	As published15.2 GB of 21.6 GB available	Full 40K
nvidia/Flora-CaptionerDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
manuelgscom/dale-0.8b-GGUFDense	752M	Q4_K_M529 MB of 21.6 GB available	Full 256K
SeerRay-Lab/Xiaomi-Lens-0Dense + vision	4.62B	As published9.24 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-0.6B-MLX-8bitDense	596M	As published615 MB of 21.6 GB available	Full 40K
LastMachine/Qwen3-8B-ZeroZero-HereticDense	8.19B	As published16.4 GB of 21.6 GB available	Full 40K
bytkim/Qwen3.8-27B-piDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-1.7B-MLX-8bitDense	1.72B	As published1.77 GB of 21.6 GB available	Full 40K
169Pi/Alpie_seedDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
Qwen/Qwen3-8B-MLX-6bitDense	8.19B	As published6.40 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-4B-MLX-8bitDense	4.02B	As published4.15 GB of 21.6 GB available	Full 40K
InternScience/Sage-A1.5MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
nvidia/NV-Reason-CTDense + vision	5.32B4.21B active	As published10.6 GB of 21.6 GB available	Full 256K
Qwen/Qwen3-1.7B-MLX-bf16Dense	1.72B	As published3.44 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-30B-A3B-MLX-8bitMoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
Qwen/Qwen3-8B-MLX-bf16Dense	8.19B	As published16.4 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-1.7B-MLX-6bitDense	1.72B	As published1.34 GB of 21.6 GB available	Full 40K
JonathanColetti/Qwen3.5-0.8B-Astra-WeightEditDense + vision	873M773M active	As published1.75 GB of 21.6 GB available	Full 256K
microsoft/AesCode-8BDense + vision	8.77B7.57B active	As published17.5 GB of 21.6 GB available	≈ 54K tokensmax 256K
Qwen/Qwen3-0.6B-MLX-6bitDense	596M	As published466 MB of 21.6 GB available	Full 40K
Qwen/Qwen3-4B-MLX-6bitDense	4.02B	As published3.14 GB of 21.6 GB available	Full 40K
Qwen/Qwen3-30B-A3B-MLX-6bitMoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
Qwen/Qwen3-14B-MLX-bf16Dense	14.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
RikiyaT/Qwen3.5-0.8B-weight-space-programmingDense + vision	873M773M active	As published1.75 GB of 21.6 GB available	Full 256K
llm-jp/llm-jp-4.1-32b-a3b-thinkingMoE	32.1B3.32B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 64K
Qwen/Qwen3-30B-A3B-MLX-bf16MoE	30.5B3.04B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 40K
gugujiji/novel-humanize-4bDense	4.02B	As published8.04 GB of 21.6 GB available	Full 40K
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-UncensoredDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Qwen/Qwen3-0.6B-MLX-bf16Dense	596M	As published1.19 GB of 21.6 GB available	Full 40K
nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16Dense + vision	8.00B	As published16.0 GB of 21.6 GB available	Full 64K
kaitchup/Qwen3.8-27B-SLQ-GGUFDense	27.3B	Q5_K_S18.9 GB of 21.6 GB available	≈ 77K tokensmax 256K
Qwen/Qwen3-4B-MLX-bf16Dense	4.02B	As published8.04 GB of 21.6 GB available	Full 40K
apple/LensVLM-9BDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
notnotsamuel/LFM2.5-350M-RLCD	354M	As published709 MB of 21.6 GB available	Full 125K
nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB	7.52B	Q4_K_M6.18 GB of 21.6 GB available	Full 64K
Jackrong/Qwopus3.8-27B-Flash-V2Dense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
Sparset/Thinklite-27BDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
briaai/fibo-scene-analyzerMoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
XingChen-AGI/Xing4.0-29B-A4B-FP8MoE	31.2B3.93B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 171K tokensmax 256K
BAAI/AREX-2Dense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
GrootTeam/Groot-19B-A3B-261023MoE + vision	19.4B3.00B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
DavidAU/Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUFDense	39.5B	IQ3_M18.3 GB of 21.6 GB available	≈ 61K tokensmax 256K
Blockway/Agens-Volundr-32B-Preview	32.7B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 81K tokensmax 256K
lightonai/colgrep-agent-2BDense	2.52B2.25B active	As published5.03 GB of 21.6 GB available	Full 128K
summerAIO/Qwen3.8-27B-Longbook27-v2Dense	27.1B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 256K
AlexWortega/Qwen3.8-27B-antislopDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
fastino/GLiDEDense + vision	26.1B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 202K tokensmax 256K
JetBrains/Mellum2.1-12B-A2.5B-ThinkingMoE	12.1B2.21B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
lightonai/LightOnOCR-3-0.8BDense + vision	853M752M active	As published1.71 GB of 21.6 GB available	Full 256K
Apexintelligence-AI/Apex-35B-V1.0MoE + vision	36.0B3.01B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 125K tokensmax 256K
Diffuspace/Clover-35B-A3B-PreviewMoE	34.7B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
huihui-ai/Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliteratedDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
lightonai/LightOnOCR-3-4BDense + vision	4.54B	As published9.08 GB of 21.6 GB available	Full 256K
Hcompany/Holo4-35B-A3BMoE + vision	35.1B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 170K tokensmax 256K
LiquidAI/LFM2.5-24B-A2B-GGUFMoE	24.0B2.45B active	Q6_K19.7 GB of 21.6 GB available	Full 128K
ML-Intern-lab/Qwen3.5-0.8B-weight-space-programmingDense + vision	873M773M active	As published1.75 GB of 21.6 GB available	Full 256K
Axion1-0/Axion-1.0-35BMoE + vision	35.1B2.95B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 170K tokensmax 256K
LiquidAI/d1-omni-600M	587M	As published2.35 GB of 21.6 GB available	Full 125K
LiquidAI/d1-3B-GGUF	2.70B	BF165.40 GB of 21.6 GB available	Full 32K
migtissera/Tess-4.5-27BDense + vision	27.8B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 173K tokensmax 256K
LiquidAI/d1-3B	3.12B	As published6.25 GB of 21.6 GB available	Full 32K
Hcompany/Holo4-27BDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
black-forest-labs/flux-3-image-klein-pupDense + vision	9.41B7.94B active	As published18.8 GB of 21.6 GB available	≈ 163K tokensmax 256K
unsloth/flint-GGUFMoE	39.8B2.52B active	UD-Q3_K_XL18.5 GB of 21.6 GB available	≈ 210K tokensmax 256K
LiquidAI/LFM2.5-24B-A2B-BaseMoE	24.0B2.45B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	Full 128K
DavidAU/Qwen3.8-27B-Jumbo-Fusion-IQ-747-900-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUFDense	27.3B	Q5_K_M19.5 GB of 21.6 GB available	≈ 57K tokensmax 256K
unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF	7.52B	BF1615.1 GB of 21.6 GB available	Full 128K
internlm/Intern-Decision-4BDense + vision	4.54B	As published9.08 GB of 21.6 GB available	Full 256K
NousResearch/Arete-27BDense + vision	27.4B	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 181K tokensmax 256K
incoai/Qwen3.8-Flash-Next-DFlash2	603M	As published1.21 GB of 21.6 GB available	Full 256K
ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUFDense	27.3B	IQ3_S12.1 GB of 21.6 GB available	Full 256K
microsoft/Mage-VL-CoworkDense + vision	4.74B4.02B active	As published9.48 GB of 21.6 GB available	≈ 160K tokensmax 256K
tencent/Hy-Memory-30B-A3BMoE	30.1B3.20B active	4-bit (estimate)no such file here: roughly what a 4-bit GGUF would take	≈ 93K tokensmax 256K

Assumes 90% of each card's memory is usable. Context memory is for one conversation. GGUF repos use their largest file that fits; other repos use the published weights, or a 4-bit estimate when only that would fit.