Benchmarks · community-measured
qwen3.6-35b-optiq-4bit on Apple M5 Max
Real measured local-inference performance for
qwen3.6-35b-optiq-4bit on an Apple M5 Max (36 GB unified memory),
from the rapid-mlx community benchmark corpus. Latest submission 2026-08-06,
measured on rapid-mlx 0.12.4.
92.9
tok/s decode
2932
tok/s prefill
734 ms
first token
22.4 GB
peak memory
Aggregated from 2 community runs.
All measurements for this pair
| RAM | Accel | Decode | Prefill | TTFT | Peak mem | Runs | rapid-mlx | Latest |
|---|---|---|---|---|---|---|---|---|
| 36 GB | — | 92.9 tok/s | 2932 tok/s | 734 ms | 22.4 GB | 2 | 0.12.4 | 2026-08-06 |
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 qwen3.6-35b-optiq-4bit --tier speed --submit