← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized

M4 Max (32c) · 36 GB · 4bit · 2026-05-11

Performance

8k

tokens

199.0

PP tok/s

17.7

TG tok/s

41158

TTFT (ms)

21.7

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	199.0	17.7	21.7 GB	current
16k	193.7	16.6	23.6 GB	view
32k	182.6	15.7	26.6 GB	view