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

Can I run ukisai_Swift-Qwen3.8-27b-GGUF on an RTX 3090?

Yes, just

Its Q5_K_M file (20.9 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 8K tokens of context.

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

Files and context on RTX 3090

Each file of ukisai_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)
BF1654.7 GBDoesn't fit——
Q8_029.1 GBDoesn't fit——
Q6_K_L25.0 GBDoesn't fit——
Q6_K23.9 GBDoesn't fit——
Q6_K_S22.9 GBDoesn't fit——
Q5_K_M20.9 GBTight8K16K
Q5_K_S19.6 GBTight28K56K
Q4_K_L18.8 GBTight39K78K
Q4_117.8 GBTight54K108K
IQ4_NL17.4 GBTight60K119K
Q4_K_M17.4 GBTight60K119K
Q4_K_S16.4 GBFits76K151K
Q4_016.3 GBFits76K152K
IQ4_XS15.5 GBFits89K178K
IQ3_M14.9 GBFits98K196K
Q3_K_L14.1 GBFits109K218K
Q3_K_M13.4 GBFits120K240K
IQ3_XS12.8 GBFits129K256K
Q3_K_S12.7 GBFits130K256K
IQ3_XXS12.3 GBFits136K256K
Q2_K10.8 GBFits158K256K
IQ2_M10.5 GBFits163K256K
IQ2_S9.68 GBFits175K256K
IQ2_XS9.09 GBFits184K256K
IQ2_XXS8.88 GBFits187K256K

ukisai_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.