RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolVLM Instruct run on the Arc B580?

Yes. At 8K context the best fit is F16, using about 5.4 GB of the 11.4 GB usable on the Arc B580. Estimated speed ceiling: ~126 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.0 GB Fits2.8 GB Fits541
3-bit (Q3_K_M)2.3 GB Fits3.0 GB Fits415
4-bit (Q4_K_M) •2.3 GB Fits3.0 GB Fits410
5-bit (Q5_K_M)2.7 GB Fits3.5 GB Fits285
6-bit (Q6_K)3.0 GB Fits3.7 GB Fits248
8-bit (Q8_0) •3.0 GB Fits3.8 GB Fits237
16-bit (F16/BF16) •4.6 GB Fits5.4 GB Fits126

• real GGUF file size from ggml-org/SmolVLM-Instruct-GGUF. Speed is a bandwidth ceiling (456 GB/s), not a benchmark. Methodology.

More

SmolVLM Instruct 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/SmolVLM-Instruct), Intel specs. Data as of 2026-11-17.