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

Can I run Swift-Qwen3.8-27B-GGUF on an RTX 3090?

Yes, just

Its Q5_K_M file (20.2 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 19K tokens of context.

Full analysis of Swift-Qwen3.8-27B-GGUF Everything that runs on RTX 3090 Get the Q5_K_M file on Hugging Face
ollama run hf.co/ukisai/Swift-Qwen3.8-27B-GGUF:Q5_K_M

Files and context on RTX 3090

Each file of Swift-Qwen3.8-27B-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)
F1654.7 GBDoesn't fit——
Q8_029.1 GBDoesn't fit——
Q6_K_L25.2 GBDoesn't fit——
Q6_K_S23.1 GBDoesn't fit——
Q6_K22.9 GBDoesn't fit——
Q5_K_M20.2 GBTight19K37K
Q5_K_S19.8 GBTight25K50K
Q4_K_L19.0 GBTight36K72K
Q4_K_M18.0 GBTight51K102K
IQ4_NL17.7 GBTight56K113K
Q4_117.5 GBTight58K117K
Q4_K_S16.6 GBFits73K145K
Q4_016.0 GBFits82K163K
IQ4_XS15.7 GBFits86K172K
IQ3_M15.1 GBFits95K190K
Q3_K_L14.3 GBFits106K212K
Q3_K_M13.6 GBFits117K233K
IQ3_XS13.0 GBFits126K251K
Q3_K_S13.0 GBFits127K253K
IQ3_XXS12.5 GBFits133K256K
Q2_K11.0 GBFits155K256K
IQ2_M10.7 GBFits160K256K
IQ2_S9.90 GBFits172K256K
IQ2_XS9.30 GBFits181K256K
IQ2_XXS9.09 GBFits184K256K

Swift-Qwen3.8-27B-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.