RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3.5 4B run on the RTX 3080 10GB?

Yes. At 8K context the best fit is Q8_0, using about 5.3 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~170 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.6 GB Fits2.8 GB Fits3.5 GB Fits6.5 GB Fits435
3-bit (Q3_K_M) •3.1 GB Fits3.3 GB Fits4.0 GB Fits7.0 GB Fits331
4-bit (Q4_K_M) •3.6 GB Fits3.7 GB Fits4.4 GB Fits7.4 GB Fits277
5-bit (Q5_K_M) •3.9 GB Fits4.1 GB Fits4.8 GB Fits7.8 GB Fits242
6-bit (Q6_K) •4.3 GB Fits4.4 GB Fits5.2 GB Fits8.2 GB Fits216
8-bit (Q8_0) •5.2 GB Fits5.3 GB Fits6.0 GB Fits9.0 GB Tight170
16-bit (F16/BF16) •8.8 GB Tight9.0 GB Tight9.7 GB No12.7 GB No90

• real GGUF file size from unsloth/Qwen3.5-4B-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.

More

Qwen3.5 4B 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

Data: Hugging Face Hub (Qwen/Qwen3.5-4B), NVIDIA specs. Data as of 2026-11-17.