M2 LLM benchmark
No M2 LLM benchmarks yet. Be the first to submit a signed, reproducible tok/s run from your own M2.
Will it run local LLMs?
No signed M2 run yet, but its 24GB of unified memory tells you what fits. At 4-bit it comfortably runs models up to about 17B parameters with room for context, and up to roughly 27B with tighter quantization. Check a specific model with the VRAM-fit tool.
For measured decode speed on the nearest hardware we have benchmarked: M3 Ultra · M4 Max · M3 Pro. Run the suite on your M2 to fill this page in.
No M2 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 M2
Direct Q&A drawn from the runs above: fastest LLM, supported model classes, backend rankings, quantization guidance.