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

Can I run Qwen3.6-27B-GGUF on an RTX 5090?

Yes, just

Its UD-Q6_K_XL file (25.6 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 45K tokens of context.

Full analysis of Qwen3.6-27B-GGUF Everything that runs on RTX 5090 Get the UD-Q6_K_XL file on Hugging Face
ollama run hf.co/unsloth/Qwen3.6-27B-GGUF:UD-Q6_K_XL

Files and context on RTX 5090

Each file of Qwen3.6-27B-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)
BF1653.8 GBDoesn't fit——
UD-Q8_K_XL35.3 GBDoesn't fit——
Q8_028.6 GBDoesn't fit7671K
UD-Q6_K_XL25.6 GBTight45K90K
Q6_K22.5 GBFits91K182K
UD-Q5_K_XL20.0 GBFits128K256K
Q5_K_M19.5 GBFits136K256K
Q5_K_S19.0 GBFits144K256K
UD-Q4_K_XL17.6 GBFits164K256K
Q4_117.3 GBFits170K256K
Q4_K_M16.8 GBFits176K256K
IQ4_NL16.1 GBFits187K256K
Q4_K_S15.9 GBFits191K256K
Q4_015.8 GBFits192K256K
IQ4_XS15.4 GBFits197K256K
UD-Q3_K_XL14.5 GBFits211K256K
Q3_K_M13.6 GBFits224K256K
Q3_K_S12.4 GBFits243K256K
UD-IQ3_XXS12.0 GBFits248K256K
UD-Q2_K_XL11.8 GBFits250K256K
UD-IQ2_M10.8 GBFits256K256K
UD-IQ2_XXS9.39 GBFits256K256K

Qwen3.6-27B-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.