← Back to community benchmarks

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

M4 Pro (16c) · 24 GB · 4bit · 2026-05-09

Performance

4k

tokens

95.7

PP tok/s

14.8

TG tok/s

42808

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	100.6	15.4	15.8 GB	view
4k	95.7	14.8	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.4	1.00×
2×	23.2	1.51×
4×	25.6	1.66×