RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM2 1.7B run on the Arc B580?

Yes. At 8K context the best fit is F16, using about 5.2 GB of the 11.4 GB usable on the Arc B580. Estimated speed ceiling: ~133 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.8 GB Fits2.6 GB Fits711
3-bit (Q3_K_M)2.0 GB Fits2.8 GB Fits545
4-bit (Q4_K_M) •2.3 GB Fits3.0 GB Fits422
5-bit (Q5_K_M)2.4 GB Fits3.1 GB Fits374
6-bit (Q6_K)2.6 GB Fits3.3 GB Fits325
8-bit (Q8_0) •3.0 GB Fits3.7 GB Fits246
16-bit (F16/BF16)4.4 GB Fits5.2 GB Fits133

• real GGUF file size from namindu94/SinhalaLLM-1.7B. Speed is a bandwidth ceiling (456 GB/s), not a benchmark. Methodology.

More

SmolLM2 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 (HuggingFaceTB/SmolLM2-1.7B), Intel specs. Data as of 2026-11-17.