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

Can I run Qwen3.6-35B-A3B-GGUF on an RTX 5090?

Yes, just

Its UD-Q5_K_XL file (26.6 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 102K tokens of context.

Full analysis of Qwen3.6-35B-A3B-GGUF Everything that runs on RTX 5090 Get the UD-Q5_K_XL file on Hugging Face
ollama run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q5_K_XL

Files and context on RTX 5090

Each file of Qwen3.6-35B-A3B-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)
BF1669.4 GBDoesn't fit——
UD-Q8_K_XL38.5 GBDoesn't fit——
Q8_036.9 GBDoesn't fit——
UD-Q6_K_XL31.8 GBDoesn't fit——
UD-Q6_K29.3 GBDoesn't fit——
UD-Q5_K_XL26.6 GBTight102K204K
UD-Q5_K_M26.5 GBTight109K217K
UD-Q5_K_S24.9 GBTight181K256K
UD-Q4_K_XL22.4 GBFits256K256K
UD-Q4_K_M22.1 GBFits256K256K
MXFP4_MOE21.7 GBFits256K256K
UD-Q4_K_S20.9 GBFits256K256K
Qwen3.6-35B-A3B-UD-IQ4_NL_XL19.5 GBFits256K256K
UD-IQ4_NL18.0 GBFits256K256K
UD-IQ4_XS17.7 GBFits256K256K
UD-Q3_K_XL16.8 GBFits256K256K
UD-Q3_K_M16.6 GBFits256K256K
UD-Q3_K_S15.4 GBFits256K256K
UD-IQ3_S13.7 GBFits256K256K
UD-IQ3_XXS13.2 GBFits256K256K
UD-Q2_K_XL12.3 GBFits256K256K
UD-IQ2_M11.5 GBFits256K256K
UD-IQ2_XXS10.8 GBFits256K256K
UD-IQ1_M10.0 GBFits256K256K

Qwen3.6-35B-A3B-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.