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

Can I run Cloudflare_clef-GGUF on an NVIDIA B200?

Yes

Its BF16 file (54.1 GB) fits in the 162 GB an NVIDIA B200 can use, with room for ≈ 256K tokens of context.

Full analysis of Cloudflare_clef-GGUF Everything that runs on NVIDIA B200 Get the BF16 file on Hugging Face
llama-server -hf bartowski/Cloudflare_clef-GGUF:BF16

Files and context on NVIDIA B200

Each file of Cloudflare_clef-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)
BF1654.1 GBFits256K256K
Q8_028.8 GBFits256K256K
Q6_K_L24.0 GBFits256K256K
Q6_K23.3 GBFits256K256K
Q5_K_M20.6 GBFits256K256K
Q5_K_S19.6 GBFits256K256K
Q4_K_L18.6 GBFits256K256K
Q4_117.7 GBFits256K256K
Q4_K_M17.7 GBFits256K256K
Q4_K_S16.6 GBFits256K256K
IQ4_NL16.3 GBFits256K256K
Q4_016.2 GBFits256K256K
IQ4_XS15.6 GBFits256K256K
Q3_K_L15.2 GBFits256K256K
Q3_K_M14.5 GBFits256K256K
IQ3_M13.8 GBFits256K256K
Q3_K_S13.6 GBFits256K256K
Q2_K11.7 GBFits256K256K

Cloudflare_clef-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.