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

Can I run XYZAILab_XYZ-Aquila-mini-GGUF on an NVIDIA H100?

Yes, just

Its BF16 file (69.4 GB) fits in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 122K tokens of context.

Full analysis of XYZAILab_XYZ-Aquila-mini-GGUF Everything that runs on NVIDIA H100 Get the BF16 file on Hugging Face
llama-server -hf bartowski/XYZAILab_XYZ-Aquila-mini-GGUF:BF16

Files and context on NVIDIA H100

Each file of XYZAILab_XYZ-Aquila-mini-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)
BF1669.4 GBTight122K244K
Q8_036.9 GBFits256K256K
Q6_K_L30.3 GBFits256K256K
Q6_K30.1 GBFits256K256K
Q5_K_L25.3 GBFits256K256K
Q5_K_M25.0 GBFits256K256K
Q5_K_S24.2 GBFits256K256K
Q4_122.0 GBFits256K256K
Q4_K_L21.8 GBFits256K256K
Q4_K_M21.4 GBFits256K256K
Q4_K_S20.6 GBFits256K256K
Q4_019.9 GBFits256K256K
IQ4_NL19.9 GBFits256K256K
IQ4_XS18.8 GBFits256K256K
Q3_K_XL17.3 GBFits256K256K
IQ3_M16.9 GBFits256K256K
Q3_K_L16.9 GBFits256K256K
Q3_K_M16.2 GBFits256K256K
IQ3_XS16.2 GBFits256K256K
Q3_K_S15.5 GBFits256K256K
IQ3_XXS14.9 GBFits256K256K
Q2_K_L13.1 GBFits256K256K
Q2_K12.6 GBFits256K256K
IQ2_M12.1 GBFits256K256K
IQ2_S11.0 GBFits256K256K
IQ2_XS10.8 GBFits256K256K
IQ2_XXS9.78 GBFits256K256K

XYZAILab_XYZ-Aquila-mini-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.