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

Can I run flint on an RTX 5090?

Yes, with a GGUF version

The published weights are too big, but the UD-Q4_K_XL file from unsloth/flint-GGUF (25.1 GB) fits, with room for ≈ 126K tokens of context.

Full analysis of flint Everything that runs on RTX 5090 Get the UD-Q4_K_XL file on Hugging Face
ollama run hf.co/unsloth/flint-GGUF:UD-Q4_K_XL

Files and context on RTX 5090

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 RTX 5090 Context (16-bit)Context (8-bit)
As published79.6 GBDoesn't fit——
BF16unsloth/flint-GGUF79.6 GBDoesn't fit——
Q8_0unsloth/flint-GGUF42.3 GBDoesn't fit——
UD-Q6_K_XLunsloth/flint-GGUF36.3 GBDoesn't fit——
UD-Q5_K_XLunsloth/flint-GGUF29.9 GBDoesn't fit——
UD-Q4_K_XLunsloth/flint-GGUF25.1 GBTight126K254K
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 RTX 5090

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.