RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 1.7B run on the Arc B580?

Yes. At 8K context the best fit is F16, using about 4.8 GB of the 11.4 GB usable on the Arc B580. Estimated speed ceiling: ~132 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.9 GB Fits2.3 GB Fits4.9 GB Fits586
3-bit (Q3_K_M) •2.0 GB Fits2.4 GB Fits5.1 GB Fits485
4-bit (Q4_K_M) •2.2 GB Fits2.6 GB Fits5.2 GB Fits412
5-bit (Q5_K_M) •2.3 GB Fits2.7 GB Fits5.4 GB Fits363
6-bit (Q6_K) •2.4 GB Fits2.9 GB Fits5.5 GB Fits322
8-bit (Q8_0) •2.8 GB Fits3.3 GB Fits5.9 GB Fits249
16-bit (F16/BF16) •4.3 GB Fits4.8 GB Fits7.4 GB Fits132

• real GGUF file size from unsloth/Qwen3-1.7B-GGUF. Speed is a bandwidth ceiling (456 GB/s), not a benchmark. Methodology.

More

Qwen3 1.7B on every GPU and Mac · Every model that runs on the Arc B580 · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3-1.7B), Intel specs. Data as of 2026-11-17.