Can I run Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF on an NVIDIA B200?

Yes

Its Q8_K file (44.5 GB) fits in the 162 GB an NVIDIA B200 can use, with room for ≈ 256K tokens of context.

Full analysis of Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF Everything that runs on NVIDIA B200 Get the Q8_K file on Hugging Face

ollama run hf.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF:Q8_K

Files and context on NVIDIA B200

Each file of Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF (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 NVIDIA B200	Context (16-bit)	Context (8-bit)
Q8_K	44.5 GB	Fits	256K	256K
Hermes3.6-35B-A3B-Uncensored-Genesis-Q8_K_P	43.6 GB	Fits	256K	256K
Hermes3.6-35B-A3B-Uncensored-Genesis-MTP-APEX	26.7 GB	Fits	256K	256K
Hermes3.6-35B-A3B-Uncensored-Genesis-APEX	25.8 GB	Fits	256K	256K
Hermes3.6-35B-A3B-Uncensored-Genesis-MTP-APEX-Compact	18.3 GB	Fits	256K	256K
Hermes3.6-35B-A3B-Uncensored-Genesis-APEX-Compact	17.4 GB	Fits	256K	256K

Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF on other hardware

Popular models that run on NVIDIA B200

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.