Benchmarks · community-measured

qwen3.6-35b-4bit on Apple M5 Pro

Real measured local-inference performance for qwen3.6-35b-4bit on an Apple M5 Pro (64 GB unified memory), from the rapid-mlx community benchmark corpus. Latest submission 2026-08-08, measured on rapid-mlx 0.12.4.

86.3
tok/s decode
867
tok/s prefill
2.4 s
first token
19.9 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

RAMAccelDecodePrefillTTFTPeak memRunsrapid-mlxLatest
64 GB86.3 tok/s867 tok/s2.4 s19.9 GB10.12.42026-08-08

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-4bit --tier speed --submit

More

Qwen family · Interactive leaderboard · Alias catalog