Benchmarks · community-measured

qwen3.5-9b-8bit on Apple M5 Max

Real measured local-inference performance for qwen3.5-9b-8bit on an Apple M5 Max (36 GB unified memory), from the rapid-mlx community benchmark corpus. Latest submission 2026-08-13, measured on rapid-mlx 0.12.10.

45.2
tok/s decode
1857
tok/s prefill
1.2 s
first token
10.4 GB
peak memory

Aggregated from 2 community runs.

All measurements for this pair

RAMAccelDecodePrefillTTFTPeak memRunsrapid-mlxLatest
36 GB45.2 tok/s1857 tok/s1.2 s10.4 GB20.12.102026-08-13

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 qwen3.5-9b-8bit --tier speed --submit

More

Qwen family · Interactive leaderboard · Alias catalog