← Back to community benchmarks

Qwen3.6-27B-oQ4

M3 Max (40c) · 64 GB · 4bit · 2026-05-04

Performance

4k

tokens

155.7

PP tok/s

14.7

TG tok/s

26307

TTFT (ms)

17.9

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	149.1	15.3	16.4 GB	view
4k	155.7	14.7	17.9 GB	current
8k	144.8	14.0	18.5 GB	view