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

Can I run Qwen3.8-27B-pi-GGUF on an NVIDIA B200?

Yes

Its BF16 file (53.8 GB) fits in the 162 GB an NVIDIA B200 can use, with room for ≈ 256K tokens of context.

Full analysis of Qwen3.8-27B-pi-GGUF Everything that runs on NVIDIA B200 Get the BF16 file on Hugging Face
ollama run hf.co/bytkim/Qwen3.8-27B-pi-GGUF:BF16

Files and context on NVIDIA B200

Each file of Qwen3.8-27B-pi-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)
BF1653.8 GBFits256K256K
Q8_028.6 GBFits256K256K
Q6_K22.1 GBFits256K256K
Q5_K_M19.2 GBFits256K256K
Q5_K_S18.7 GBFits256K256K
Q4_K_M16.5 GBFits256K256K
IQ4_NL15.8 GBFits256K256K
Q4_K_S15.6 GBFits256K256K
IQ4_XS15.1 GBFits256K256K
Q3_K_L14.3 GBFits256K256K
Q3_K_M13.3 GBFits256K256K
IQ3_M12.6 GBFits256K256K
Q3_K_S12.1 GBFits256K256K
IQ3_XS12.0 GBFits256K256K
Q2_K10.7 GBFits256K256K
IQ2_M10.0 GBFits256K256K
IQ2_S9.36 GBFits256K256K
IQ2_XS9.09 GBFits256K256K

Qwen3.8-27B-pi-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.