How fast is Intel Arc B580 12GB for local AI workloads?
Intel Arc B580 12GB hits 86.0 tok/s on Phi-3 Mini, its strongest benchmarked workload (batch 1, 4096-token context, 12GB VRAM, 190W TDP). It has 11 records across 7 workloads in our database, with a MyAI Rating of 8.4/10. Llama 3 70B Q4 needs ~40GB VRAM, so check the VRAM column before assuming feasibility.