← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Pro (16c) · 32 GB · 4bit · 2026-05-08

Performance

4k

tokens

49.5

PP tok/s

10.6

TG tok/s

82830

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.9.dev1

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	49.0	10.9	16.8 GB	view
4k	49.5	10.6	18.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	10.9	1.00×
2×	12.4	1.14×
4×	12.8	1.17×