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

Can I run gemma-4-26B-A4B-it-GGUF on an NVIDIA H100?

Yes

Its BF16 file (50.5 GB) fits in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 251K tokens of context.

Full analysis of gemma-4-26B-A4B-it-GGUF Everything that runs on NVIDIA H100 Get the BF16 file on Hugging Face
llama-server -hf unsloth/gemma-4-26B-A4B-it-GGUF:BF16

Files and context on NVIDIA H100

Each file of gemma-4-26B-A4B-it-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 H100 Context (16-bit)Context (8-bit)
BF1650.5 GBFits251K256K
UD-Q8_K_XL27.6 GBFits256K256K
Q8_026.9 GBFits256K256K
UD-Q6_K_XL23.3 GBFits256K256K
UD-Q6_K23.2 GBFits256K256K
UD-Q5_K_XL21.2 GBFits256K256K
UD-Q5_K_M21.2 GBFits256K256K
UD-Q5_K_S18.9 GBFits256K256K
UD-Q4_K_XL17.0 GBFits256K256K
UD-Q4_K_M16.9 GBFits256K256K
MXFP4_MOE16.6 GBFits256K256K
UD-Q4_K_S16.5 GBFits256K256K
UD-IQ4_NL13.6 GBFits256K256K
UD-IQ4_XS13.6 GBFits256K256K
UD-Q3_K_XL12.9 GBFits256K256K
UD-Q3_K_M12.7 GBFits256K256K
UD-IQ3_XXS11.4 GBFits256K256K
UD-IQ3_S11.3 GBFits256K256K
UD-Q2_K_XL10.5 GBFits256K256K
UD-IQ2_M10.0 GBFits256K256K
UD-IQ2_XXS9.92 GBFits256K256K

gemma-4-26B-A4B-it-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.