Can I run Gemma-4-31B-Humanlike-Chat-GGUF on an NVIDIA H100?

Yes, just

Its BF16 file (61.4 GB) fits in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 27K tokens of context.

Full analysis of Gemma-4-31B-Humanlike-Chat-GGUF Everything that runs on NVIDIA H100 Get the BF16 file on Hugging Face

llama-server -hf LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-GGUF:BF16

Files and context on NVIDIA H100

Each file of Gemma-4-31B-Humanlike-Chat-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)
BF16	61.4 GB	Tight	27K	58K
Q8_0	32.6 GB	Fits	112K	230K
Q6_K	25.2 GB	Fits	134K	256K
Q5_K_M	21.8 GB	Fits	144K	256K
Q4_K_M	18.7 GB	Fits	154K	256K
IQ4_XS	16.7 GB	Fits	160K	256K

Gemma-4-31B-Humanlike-Chat-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.