Benchmarks · community-measured

qwen3.5-4b-4bit on Apple M4 Max

Real measured local-inference performance for qwen3.5-4b-4bit on an Apple M4 Max (64 GB unified memory), from the rapid-mlx community benchmark corpus. Latest submission 2026-08-14, measured on rapid-mlx 0.12.11.

138
tok/s decode
1243
tok/s prefill
1.7 s
first token
5.3 GB
peak memory

Aggregated from 2 community runs.

All measurements for this pair

RAMAccelDecodePrefillTTFTPeak memRunsrapid-mlxLatest
64 GB138 tok/s1243 tok/s1.7 s5.3 GB20.12.112026-08-14

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