Everything built on Qwen3.6-35B-A3B

11 models built on Qwen/Qwen3.6-35B-A3B that Model Anatomy has analyzed: 7 quantizations, 3 fine-tunes, 1 adapter.

Qwen/Qwen3.6-35B-A3B36.0B · 3.01B activeRuns on 24 GB as GGUF

Qwen/Qwen3.6-35B-A3B-FP8quantization36.0B · 3.01B active24 GB if quantized
unsloth/Qwen3.6-35B-A3B-NVFP4quantization36.0B · 3.01B activeRuns on 32 GB
unsloth/Qwen3.6-35B-A3B-GGUFquantization34.7B · 2.95B activeRuns on 12 GB
unsloth/Qwen3.6-35B-A3B-MTP-GGUFquantization35.5B · 2.95B activeRuns on 16 GB
RedHatAI/Qwen3.6-35B-A3B-NVFP4quantization36.0B · 3.01B activeRuns on 32 GB
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressivequantization34.7B · 2.95B activeRuns on 16 GB
Bahushruth/Qwen3.6-35B-A3B-abliterated-v4fine-tune34.7B · 2.95B active24 GB if quantized
empero-ai/Qwen3.8-35B-A3B-Distillfine-tune36.0B · 3.01B activeRuns on 24 GB as GGUF
- empero-ai/Qwen3.8-35B-A3B-Distill-GGUFquantization35.5B · 2.95B activeRuns on 16 GB
Accio-Lab/occamy-1.0fine-tune35.1B · 2.95B active24 GB if quantized
Edge0/Edge0-35B-A3B-previewadapter34.7B · 2.95B activeRuns on 24 GB

Built from what each repo's own tags say it was made from, so a fine-tune its author didn't tag won't appear, and only models Model Anatomy has analyzed are listed. Each name opens the model's full analysis; the GPU badge opens the answer for that card.