← Back to community benchmarks

Qwen3.6-27B-OptiQ

M5 Pro (16c) · 48 GB · 4bit · 2026-06-17

Performance

4k

tokens

377.2

PP tok/s

14.7

TG tok/s

10858

TTFT (ms)

20.6

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.4.4rc2

macOS macOS 26.5.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	351.6	14.8	19.2 GB	view
4k	377.2	14.7	20.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	14.8	1.00×
2×	25.0	1.69×
4×	31.4	2.12×