Can I run Nanbeige4.3-33B-GSQ-RCO-GGUF on an NVIDIA H100?

Yes

Its Q5_K_M file (23.8 GB) fits in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 221K tokens of context.

Full analysis of Nanbeige4.3-33B-GSQ-RCO-GGUF Everything that runs on NVIDIA H100 Get the Q5_K_M file on Hugging Face

ollama run hf.co/abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:Q5_K_M

Files and context on NVIDIA H100

Each file of Nanbeige4.3-33B-GSQ-RCO-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 H100	Context (16-bit)	Context (8-bit)
Q5_K_M	23.8 GB	Fits	221K	442K
IQ4_XS	18.7 GB	Fits	244K	489K
IQ3_M	16.1 GB	Fits	256K	512K
IQ3_XS	14.8 GB	Fits	262K	512K
IQ2_M	12.7 GB	Fits	272K	512K
IQ2_XS	10.9 GB	Fits	280K	512K
IQ2_XXS	9.90 GB	Fits	285K	512K

Nanbeige4.3-33B-GSQ-RCO-GGUF on other hardware

Popular models that run on NVIDIA H100

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.