M2 LLM benchmark
No signed M2 submissions yet. Check the configuration guidance below, or contribute a reproducible measurement from your own machine.
Specs vendor specs, not measured
- Unified memory (max configuration)
- 24 GB
Plan memory before choosing a model
The catalog lists a family maximum of 24 GB of unified memory. Enter your installed amount; smaller configurations have less space. Model weights, context cache and runtime overhead must share the available memory. Capacity alone does not establish which model will fit or how fast it will run. Use the memory-fit calculator for your model and context as an estimate, then verify with the intended runtime. No signed M2 measurement is available yet.
Contribute a signed M2 benchmark
Run on YOUR hardware to populate this page: pipx install llm-speed && llm-speed bench
$ pipx install llm-speed && llm-speed bench
Request a run on M2
No measured run yet for these pairs. Vote for the one you want; the most-requested runs go first. See all requests.
We never sell or share your email. Privacy