← Back to community benchmarks

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

M4 Pro (20c) · 48 GB · 4bit · 2026-05-18

Performance

1k

tokens

124.4

PP tok/s

15.5

TG tok/s

8232

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	124.4	15.5	15.8 GB	current
4k	126.0	13.8	17.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.5	1.00×
2×	29.2	1.88×
4×	32.7	2.11×