← Back to community benchmarks

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

M4 Pro (20c) · 64 GB · 4bit · 2026-06-19

Performance

8k

tokens

125.2

PP tok/s

15.0

TG tok/s

65437

TTFT (ms)

18.3

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	124.6	15.7	15.8 GB	view
4k	126.5	15.3	17.3 GB	view
8k	125.2	15.0	18.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.7	1.00×
2×	29.6	1.89×
4×	32.6	2.08×