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

Can I run Swift-Qwen3.8-27B-GGUF on an RTX 5090?

Yes, just

Its Q6_K_L file (25.2 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 52K tokens of context.

Full analysis of Swift-Qwen3.8-27B-GGUF Everything that runs on RTX 5090 Get the Q6_K_L file on Hugging Face
ollama run hf.co/ukisai/Swift-Qwen3.8-27B-GGUF:Q6_K_L

Files and context on RTX 5090

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 5090 Context (16-bit)Context (8-bit)
F1654.7 GBDoesn't fit——
Q8_029.1 GBDoesn't fit——
Q6_K_L25.2 GBTight52K104K
Q6_K_S23.1 GBTight83K166K
Q6_K22.9 GBFits86K172K
Q5_K_M20.2 GBFits126K252K
Q5_K_S19.8 GBFits132K256K
Q4_K_L19.0 GBFits143K256K
Q4_K_M18.0 GBFits158K256K
IQ4_NL17.7 GBFits164K256K
Q4_117.5 GBFits166K256K
Q4_K_S16.6 GBFits180K256K
Q4_016.0 GBFits189K256K
IQ4_XS15.7 GBFits193K256K
IQ3_M15.1 GBFits202K256K
Q3_K_L14.3 GBFits213K256K
Q3_K_M13.6 GBFits224K256K
IQ3_XS13.0 GBFits233K256K
Q3_K_S13.0 GBFits234K256K
IQ3_XXS12.5 GBFits240K256K
Q2_K11.0 GBFits256K256K
IQ2_M10.7 GBFits256K256K
IQ2_S9.90 GBFits256K256K
IQ2_XS9.30 GBFits256K256K
IQ2_XXS9.09 GBFits256K256K

Swift-Qwen3.8-27B-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.