← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Speed

M1 Max (32c) · 64 GB · 4bit · 2026-05-14

Performance

4k

tokens

153.8

PP tok/s

19.5

TG tok/s

26636

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	149.1	20.2	15.8 GB	view
4k	153.8	19.5	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	20.2	1.00×
2×	29.5	1.46×
4×	59.0	2.92×