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

Can I run NousResearch_Arete-27B-GGUF on an RTX 3090?

Yes, just

Its Q5_K_M file (20.7 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 11K tokens of context.

Full analysis of NousResearch_Arete-27B-GGUF Everything that runs on RTX 3090 Get the Q5_K_M file on Hugging Face
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q5_K_M

Files and context on RTX 3090

Each file of NousResearch_Arete-27B-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 3090 Context (16-bit)Context (8-bit)
BF1653.8 GBDoesn't fit——
Q8_028.7 GBDoesn't fit——
Q6_K_L24.7 GBDoesn't fit——
Q6_K23.6 GBDoesn't fit——
Q6_K_S22.6 GBDoesn't fit——
Q5_K_M20.7 GBTight11K23K
Q5_K_S19.3 GBTight32K63K
Q4_K_L18.6 GBTight43K85K
Q4_117.6 GBTight58K115K
IQ4_NL17.2 GBFits63K126K
Q4_K_M17.2 GBFits63K126K
Q4_K_S16.1 GBFits79K159K
Q4_016.1 GBFits80K159K
IQ4_XS15.2 GBFits93K185K
IQ3_M14.6 GBFits102K203K
Q3_K_L13.9 GBFits113K225K
Q3_K_M13.2 GBFits123K247K
IQ3_XS12.6 GBFits132K256K
Q3_K_S12.5 GBFits133K256K
IQ3_XXS12.1 GBFits140K256K
Q2_K10.6 GBFits162K256K
IQ2_M10.3 GBFits166K256K
IQ2_S9.45 GBFits179K256K
IQ2_XS8.85 GBFits188K256K
IQ2_XXS8.64 GBFits191K256K

NousResearch_Arete-27B-GGUF on other hardware

Popular models that run on RTX 3090

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.