← Back to community benchmarks

Qwen3.6-27B-oQ6-fp16-mtp

M2 Pro (16c) · 32 GB · 6bit · 2026-05-16

Performance

1k

tokens

80.0

PP tok/s

10.3

TG tok/s

12807

TTFT (ms)

23.0

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 32 GB

GPU Cores 16

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	80.0	10.3	23.0 GB	current
4k	80.9	8.8	24.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	10.3	1.00×
2×	11.6	1.13×
4×	12.2	1.18×