← Back to community benchmarks

Qwen3.6-27B-oQ4-fp16-mtp

M1 Max (32c) · 64 GB · 4bit · 2026-05-17

User commentwith MTP

Performance

4k

tokens

93.9

PP tok/s

13.8

TG tok/s

43644

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9.dev1

macOS macOS 15.6.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	90.9	16.3	16.7 GB	view
4k	93.9	13.8	18.2 GB	current
8k	86.8	14.1	19.2 GB	view
16k	77.1	12.8	20.7 GB	view