← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 4bit · 2026-05-16

Performance

4k

tokens

189.9

PP tok/s

19.0

TG tok/s

21573

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	205.3	23.1	15.8 GB	view
4k	189.9	19.0	17.3 GB	current
8k	182.8	17.9	18.3 GB	view
16k	158.4	10.9	19.8 GB	view
32k	120.2	9.0	22.8 GB	view