Can I run ThinkingCap-Qwen3.8-27B-NVFP4 on an RTX 3090?

Yes, just

Its published weights (20.6 GB) fit in the 21.6 GB an RTX 3090 can use, with room for ≈ 13K tokens of context.

Full analysis of ThinkingCap-Qwen3.8-27B-NVFP4 Everything that runs on RTX 3090 Get the weights on Hugging Face

hf download bottlecapai/ThinkingCap-Qwen3.8-27B-NVFP4

Files and context on RTX 3090

Each file of ThinkingCap-Qwen3.8-27B-NVFP4 (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On RTX 3090	Context (16-bit)	Context (8-bit)
As published	20.6 GB	Tight	13K	25K
4-bit (estimate)	15.6 GB	Fits	87K	173K

ThinkingCap-Qwen3.8-27B-NVFP4 on other hardware

NVIDIA H100Yes
RTX 5090Yes
RTX 4090Yes, just
RTX 3090Yes, just
RTX 5060 Ti 16 GBNo
RTX 3060 12 GBNo
RTX 4060No
Mac with 32 GBYes, just
Mac with 64 GBYes
Mac with 128 GBYes

Popular models that run on RTX 3090

Qwen3-0.6BQwen · 752M
Qwen3-VL-8B-InstructQwen · 8.77B
gpt2openai-community · 137M
Qwen3-8BQwen · 8.19B
Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth · 30.5B
Qwen2.5-7B-InstructQwen · 7.62B
Qwen3.5-9BQwen · 9.65B
Qwen2.5-0.5B-InstructQwen · 494M

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.