Benchmarks · community-measured
gpt-oss-20b-mxfp4-q8 on Apple M2 Pro
Real measured local-inference performance for
gpt-oss-20b-mxfp4-q8 on an Apple M2 Pro (32 GB unified memory),
from the rapid-mlx community benchmark corpus. Latest submission 2026-08-02,
measured on rapid-mlx 0.11.9.
44.6
tok/s decode
282
tok/s prefill
7.5 s
first token
12.0 GB
peak memory
A single community run so far — treat it as one data point, not a distribution. Reproduce it below and submit yours to firm it up.
All measurements for this pair
| RAM | Accel | Decode | Prefill | TTFT | Peak mem | Runs | rapid-mlx | Latest |
|---|---|---|---|---|---|---|---|---|
| 32 GB | — | 44.6 tok/s | 282 tok/s | 7.5 s | 12.0 GB | 1 | 0.11.9 | 2026-08-02 |
Standardized single-request benchmark: 5 measured rounds after 1 discarded warmup, greedy sampling, prefix cache disabled. Raw corpus: /api/benchmarks.
Reproduce this number
Install rapid-mlx, run the same suite on your Mac, and submit the result — it lands on the community leaderboard and updates this page.
$ curl -fsSL https://rapidmlx.com/install.sh | bash
$ rapid-mlx bench gpt-oss-20b-mxfp4-q8 --tier speed --submit