Skip to content
llm-speed

Arc B580 LLM benchmark

No Arc B580 LLM benchmarks yet. Be the first to submit a signed, reproducible tok/s run from your own Arc B580.

Will it run local LLMs?

No signed Arc B580 run yet, but its 12GB of VRAM tells you what fits. At 4-bit it comfortably runs models up to about 11B parameters with room for context, and up to roughly 17B with tighter quantization. Check a specific model with the VRAM-fit tool.

No Arc B580 benchmarks yet.

Run on YOUR hardware to populate this page: pipx install llm-speed && llm-speed bench

$ pipx install llm-speed && llm-speed bench

Common questions about Arc B580

Direct Q&A drawn from the runs above: fastest LLM, supported model classes, backend rankings, quantization guidance.

Read the Arc B580 FAQ →