← Back to community benchmarks

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

M4 Pro (20c) · 24 GB · 4bit · 2026-05-23

Performance

4k

tokens

126.2

PP tok/s

14.8

TG tok/s

32461

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 24 GB

GPU Cores 20

Software

oMLX v0.3.9

macOS macOS 15.7.7

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	124.1	15.6	15.8 GB	view
4k	126.2	14.8	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.6	1.00×
2×	29.6	1.90×
4×	32.4	2.08×