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

Can I run flint on an NVIDIA H100?

Yes, with a GGUF version

The published weights are too big, but the Q8_0 file from unsloth/flint-GGUF (42.3 GB) fits, with room for ≈ 256K tokens of context.

Full analysis of flint Everything that runs on NVIDIA H100 Get the Q8_0 file on Hugging Face
ollama run hf.co/unsloth/flint-GGUF:Q8_0

Files and context on NVIDIA H100

Each file of flint (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)
As published79.6 GBDoesn't fit——
BF16unsloth/flint-GGUF79.6 GBDoesn't fit——
Q8_0unsloth/flint-GGUF42.3 GBFits256K256K
UD-Q6_K_XLunsloth/flint-GGUF36.3 GBFits256K256K
UD-Q5_K_XLunsloth/flint-GGUF29.9 GBFits256K256K
UD-Q4_K_XLunsloth/flint-GGUF25.1 GBFits256K256K
UD-Q3_K_XLunsloth/flint-GGUF18.5 GBFits256K256K
UD-IQ3_XXSunsloth/flint-GGUF14.5 GBFits256K256K
UD-Q2_K_XLunsloth/flint-GGUF13.6 GBFits256K256K
UD-IQ2_XXSunsloth/flint-GGUF11.9 GBFits256K256K
UD-IQ1_Munsloth/flint-GGUF11.4 GBFits256K256K

flint 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.