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

Can I run flint-GGUF on an RTX 4090?

Yes, just

Its UD-Q3_K_XL file (18.5 GB) fits in the 21.6 GB an RTX 4090 can use, with room for ≈ 105K tokens of context.

Full analysis of flint-GGUF Everything that runs on RTX 4090 Get the UD-Q3_K_XL file on Hugging Face
ollama run hf.co/unsloth/flint-GGUF:UD-Q3_K_XL

Files and context on RTX 4090

Each file of flint-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 RTX 4090 Context (16-bit)Context (8-bit)
BF1679.6 GBDoesn't fit——
Q8_042.3 GBDoesn't fit——
UD-Q6_K_XL36.3 GBDoesn't fit——
UD-Q5_K_XL29.9 GBDoesn't fit——
UD-Q4_K_XL25.1 GBDoesn't fit——
UD-Q3_K_XL18.5 GBTight105K210K
UD-IQ3_XXS14.5 GBFits239K256K
UD-Q2_K_XL13.6 GBFits256K256K
UD-IQ2_XXS11.9 GBFits256K256K
UD-IQ1_M11.4 GBFits256K256K

flint-GGUF on other hardware

Popular models that run on RTX 4090

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.