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

Can I run Qwen3-Coder-30B-A3B-Instruct-GGUF on an RTX 5090?

Yes, just

Its UD-Q6_K_XL file (26.3 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 24K tokens of context.

Full analysis of Qwen3-Coder-30B-A3B-Instruct-GGUF Everything that runs on RTX 5090 Get the UD-Q6_K_XL file on Hugging Face
ollama run hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:UD-Q6_K_XL

Files and context on RTX 5090

Each file of Qwen3-Coder-30B-A3B-Instruct-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)
BF1661.1 GBDoesn't fit——
UD-Q8_K_XL36.0 GBDoesn't fit——
Q8_032.5 GBDoesn't fit——
UD-Q6_K_XL26.3 GBTight24K49K
Q6_K25.1 GBTight37K74K
UD-Q5_K_XL21.7 GBFits70K140K
Q5_K_M21.7 GBFits70K141K
Q5_K_S21.1 GBFits77K153K
Q4_119.2 GBFits95K191K
Q4_K_M18.6 GBFits102K204K
UD-Q4_K_XL17.7 GBFits111K221K
Q4_K_S17.5 GBFits113K225K
Q4_017.4 GBFits113K227K
IQ4_NL17.3 GBFits114K228K
IQ4_XS16.4 GBFits123K247K
Q3_K_M14.7 GBFits140K256K
UD-Q3_K_XL13.8 GBFits149K256K
Q3_K_S13.3 GBFits154K256K
UD-IQ3_XXS12.8 GBFits158K256K
UD-Q2_K_XL11.8 GBFits169K256K
Q2_K_L11.3 GBFits174K256K
Q2_K11.3 GBFits174K256K
UD-IQ2_M10.8 GBFits178K256K
UD-IQ2_XXS10.3 GBFits183K256K
UD-IQ1_M9.63 GBFits190K256K
UD-IQ1_S8.91 GBFits198K256K
UD-TQ1_08.01 GBFits207K256K

Qwen3-Coder-30B-A3B-Instruct-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.