RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Qwen3.5 9B run on the RTX 3080 10GB?

Yes. At 8K context the best fit is Q6_K, using about 8.5 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~95 tokens/sec.

+ 0.9 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q6_K at 8K context then needs about 9.4 GB (tight). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •5.0 GB Fits5.1 GB Fits5.9 GB Fits8.9 GB Tight176
3-bit (Q3_K_M) •5.8 GB Fits5.9 GB Fits6.7 GB Fits9.7 GB No147
4-bit (Q4_K_M) •6.7 GB Fits6.9 GB Fits7.6 GB Fits10.6 GB No123
5-bit (Q5_K_M) •7.6 GB Fits7.7 GB Fits8.5 GB Fits11.5 GB No107
6-bit (Q6_K) •8.4 GB Fits8.5 GB Fits9.3 GB Tight12.3 GB No95
8-bit (Q8_0) •10.1 GB No10.3 GB No11.0 GB No14.0 GB No—
16-bit (F16/BF16) •18.1 GB No18.3 GB No19.0 GB No22.0 GB No—

• real GGUF file size from bartowski/Qwen_Qwen3.5-9B-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Qwen3.5 9B on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (Qwen/Qwen3.5-9B), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.