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

Can I run Qwen3.5-9B on an RTX 5080?

Yes, with a GGUF version

The published weights are too big, but the UD-Q8_K_XL file from unsloth/Qwen3.5-9B-GGUF (13.0 GB) fits, with room for ≈ 41K tokens of context.

Full analysis of Qwen3.5-9B Everything that runs on RTX 5080 Get the UD-Q8_K_XL file on Hugging Face
ollama run hf.co/unsloth/Qwen3.5-9B-GGUF:UD-Q8_K_XL

Files and context on RTX 5080

Each file of Qwen3.5-9B (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 5080 Context (16-bit)Context (8-bit)
As published19.3 GBDoesn't fit——
BF16unsloth/Qwen3.5-9B-GGUF17.9 GBDoesn't fit——
UD-Q8_K_XLunsloth/Qwen3.5-9B-GGUF13.0 GBTight41K82K
Q8_0unsloth/Qwen3.5-9B-GGUF9.53 GBFits144K256K
UD-Q6_K_XLunsloth/Qwen3.5-9B-GGUF8.76 GBFits167K256K
Q6_Kunsloth/Qwen3.5-9B-GGUF7.46 GBFits205K256K
UD-Q5_K_XLunsloth/Qwen3.5-9B-GGUF6.74 GBFits227K256K
Q5_K_Munsloth/Qwen3.5-9B-GGUF6.58 GBFits232K256K
Q5_K_Sunsloth/Qwen3.5-9B-GGUF6.36 GBFits238K256K
UD-Q4_K_XLunsloth/Qwen3.5-9B-GGUF5.97 GBFits250K256K
Q4_1unsloth/Qwen3.5-9B-GGUF5.84 GBFits254K256K
Q4_K_Munsloth/Qwen3.5-9B-GGUF5.68 GBFits256K256K
Q4_K_Sunsloth/Qwen3.5-9B-GGUF5.39 GBFits256K256K
Q4_0unsloth/Qwen3.5-9B-GGUF5.38 GBFits256K256K
IQ4_NLunsloth/Qwen3.5-9B-GGUF5.37 GBFits256K256K
IQ4_XSunsloth/Qwen3.5-9B-GGUF5.17 GBFits256K256K
UD-Q3_K_XLunsloth/Qwen3.5-9B-GGUF5.05 GBFits256K256K
Q3_K_Munsloth/Qwen3.5-9B-GGUF4.67 GBFits256K256K
Q3_K_Sunsloth/Qwen3.5-9B-GGUF4.32 GBFits256K256K
UD-Q2_K_XLunsloth/Qwen3.5-9B-GGUF4.12 GBFits256K256K
UD-IQ3_XXSunsloth/Qwen3.5-9B-GGUF4.02 GBFits256K256K
UD-IQ2_Munsloth/Qwen3.5-9B-GGUF3.65 GBFits256K256K
UD-IQ2_XXSunsloth/Qwen3.5-9B-GGUF3.19 GBFits256K256K

Qwen3.5-9B on other hardware

Popular models that run on RTX 5080

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.