Can I run Sharp-MiniCPM5-2B-GGUF on an NVIDIA B200?

Yes

Its Q8_K_M file (2.93 GB) fits in the 162 GB an NVIDIA B200 can use, with room for ≈ 128K tokens of context.

Full analysis of Sharp-MiniCPM5-2B-GGUF Everything that runs on NVIDIA B200 Get the Q8_K_M file on Hugging Face

ollama run hf.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q8_K_M

Files and context on NVIDIA B200

Each file of Sharp-MiniCPM5-2B-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_M	2.93 GB	Fits	128K	128K
Q6_K_XL	2.20 GB	Fits	128K	128K
Q5_K_XL	1.89 GB	Fits	128K	128K
Q4_K_XL	1.60 GB	Fits	128K	128K
Q4_K_S	1.52 GB	Fits	128K	128K

Sharp-MiniCPM5-2B-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.