← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 4bit · 2026-05-19

Performance

8k

tokens

88.3

PP tok/s

17.7

TG tok/s

92801

TTFT (ms)

18.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 15.6.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	87.2	19.2	15.8 GB	view
4k	88.6	18.4	17.3 GB	view
8k	88.3	17.7	18.3 GB	current
16k	86.6	16.1	19.8 GB	view
32k	83.3	14.9	22.8 GB	view
64k	74.9	11.9	28.8 GB	view