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

Can I run Cloudflare_clef-GGUF on an RTX 5090?

Yes, just

Its Q6_K_L file (24.0 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 70K tokens of context.

Full analysis of Cloudflare_clef-GGUF Everything that runs on RTX 5090 Get the Q6_K_L file on Hugging Face
ollama run hf.co/bartowski/Cloudflare_clef-GGUF:Q6_K_L

Files and context on RTX 5090

Each file of Cloudflare_clef-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 5090 Context (16-bit)Context (8-bit)
BF1654.1 GBDoesn't fit——
Q8_028.8 GBDoesn't fit——
Q6_K_L24.0 GBTight70K140K
Q6_K23.3 GBTight79K158K
Q5_K_M20.6 GBFits119K239K
Q5_K_S19.6 GBFits135K256K
Q4_K_L18.6 GBFits150K256K
Q4_117.7 GBFits163K256K
Q4_K_M17.7 GBFits164K256K
Q4_K_S16.6 GBFits180K256K
IQ4_NL16.3 GBFits184K256K
Q4_016.2 GBFits186K256K
IQ4_XS15.6 GBFits195K256K
Q3_K_L15.2 GBFits201K256K
Q3_K_M14.5 GBFits211K256K
IQ3_M13.8 GBFits222K256K
Q3_K_S13.6 GBFits224K256K
Q2_K11.7 GBFits252K256K

Cloudflare_clef-GGUF 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.