← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Quality

M3 Max (40c) · 64 GB · 4bit · 2026-05-15

Performance

16k

tokens

163.4

PP tok/s

11.2

TG tok/s

100272

TTFT (ms)

31.7

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 16,384