← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M1 Max (32c) · 64 GB · 4bit · 2026-05-21

Performance

1k

tokens

82.8

PP tok/s

17.3

TG tok/s

12363

TTFT (ms)

16.7

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	82.8	17.3	16.7 GB	current
4k	84.1	16.6	18.2 GB	view
8k	82.7	16.0	19.2 GB	view