← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 128 GB · 8bit · 2026-05-10

Performance

32k

tokens

201.7

PP tok/s

21.5

TG tok/s

162469

TTFT (ms)

35.8

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.3.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	209.9	22.0	32.1 GB	view
32k	201.7	21.5	35.8 GB	current
64k	178.7	19.2	41.8 GB	view