← Back to community benchmarks

Qwen3.6-27B-OptiQ

M1 Max (32c) · 64 GB · 4bit · 2026-06-21

Performance

8k

tokens

89.7

PP tok/s

16.2

TG tok/s

91293

TTFT (ms)

21.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	88.7	17.0	19.2 GB	view
4k	90.6	16.3	20.6 GB	view
8k	89.7	16.2	21.3 GB	current