Model Anatomy See what's inside open-weight AI models

Can I run Qwen3-235B-A22B-GGUF on an NVIDIA B200?

Yes, just

Its Q4_K_M file (142 GB) fits in the 162 GB an NVIDIA B200 can use, with room for ≈ 40K tokens of context.

Full analysis of Qwen3-235B-A22B-GGUF Everything that runs on NVIDIA B200 Get the Q4_K_M file on Hugging Face
llama-server -hf Qwen/Qwen3-235B-A22B-GGUF:Q4_K_M

Files and context on NVIDIA B200

Each file of Qwen3-235B-A22B-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.

FileSizeOn NVIDIA B200 Context (16-bit)Context (8-bit)
Q8_0250 GBDoesn't fit——
Q6_K193 GBDoesn't fit——
Q5_K_M167 GBDoesn't fit——
Q5_0162 GBDoesn't fit6151K
Q4_K_M142 GBTight40K40K

Qwen3-235B-A22B-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.