← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (32c) · 36 GB · 4bit · 2026-05-08

Performance

4k

tokens

176.8

PP tok/s

28.5

TG tok/s

23164

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	192.2	31.8	16.8 GB	view
4k	176.8	28.5	18.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	31.8	1.00×
2×	62.6	1.97×
4×	89.4	2.81×