← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized

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

Performance

16k

tokens

193.7

PP tok/s

16.6

TG tok/s

84568

TTFT (ms)

23.6

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 16,384

Performance by Context Length

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