Benchmarks · community-measured
qwen3.5-4b-4bit on Apple M2 Pro
Real measured local-inference performance for
qwen3.5-4b-4bit 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.
56.4
tok/s decode
308
tok/s prefill
6.9 s
first token
3.9 GB
peak memory
Aggregated from 3 community runs.
All measurements for this pair
| RAM | Accel | Decode | Prefill | TTFT | Peak mem | Runs | rapid-mlx | Latest |
|---|---|---|---|---|---|---|---|---|
| 32 GB | — | 56.4 tok/s | 308 tok/s | 6.9 s | 3.9 GB | 3 | 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 qwen3.5-4b-4bit --tier speed --submit
More
qwen3.5-4b-4bit model page · Qwen family · Interactive leaderboard · Alias catalog