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

Can I run Qwen3.6-27B-MTP-GGUF on an RTX 4090?

Yes, just

Its UD-Q5_K_XL file (20.4 GB) fits in the 21.6 GB an RTX 4090 can use, with room for ≈ 16K tokens of context.

Full analysis of Qwen3.6-27B-MTP-GGUF Everything that runs on RTX 4090 Get the UD-Q5_K_XL file on Hugging Face
ollama run hf.co/unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q5_K_XL

Files and context on RTX 4090

Each file of Qwen3.6-27B-MTP-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 4090 Context (16-bit)Context (8-bit)
BF1654.7 GBDoesn't fit——
UD-Q8_K_XL35.8 GBDoesn't fit——
Q8_029.0 GBDoesn't fit——
UD-Q6_K_XL26.0 GBDoesn't fit——
Q6_K22.9 GBDoesn't fit——
UD-Q5_K_XL20.4 GBTight16K33K
Q5_K_M19.8 GBTight24K48K
Q5_K_S19.3 GBTight32K65K
UD-Q4_K_XL17.9 GBTight53K105K
Q4_117.5 GBTight58K116K
Q4_K_M17.1 GBFits65K129K
IQ4_NL16.3 GBFits76K152K
Q4_K_S16.1 GBFits79K159K
Q4_016.1 GBFits80K161K
IQ4_XS15.7 GBFits86K171K
UD-Q3_K_XL14.8 GBFits99K198K
Q3_K_M13.8 GBFits114K227K
Q3_K_S12.6 GBFits132K256K
UD-IQ3_XXS12.2 GBFits138K256K
UD-Q2_K_XL12.0 GBFits140K256K
UD-IQ2_M11.0 GBFits155K256K
UD-IQ2_XXS9.57 GBFits177K256K

Qwen3.6-27B-MTP-GGUF on other hardware

Popular models that run on RTX 4090

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.