← Back to community benchmarks

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

M4 Pro (16c) · 64 GB · 4bit · 2026-05-21

Performance

16k

tokens

92.2

PP tok/s

13.0

TG tok/s

177790

TTFT (ms)

19.8

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 15.7.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	92.5	18.0	19.5 GB	view
4k	95.2	14.6	17.3 GB	view
8k	93.0	14.0	18.3 GB	view
16k	92.2	13.0	19.8 GB	current