← Back to community benchmarks

Qwen3.6-27B-MTP-Optimized

M3 Max (40c) · 48 GB · 4bit · 2026-05-13

Performance

8k

tokens

198.3

PP tok/s

21.9

TG tok/s

41307

TTFT (ms)

18.3

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	210.2	23.1	15.8 GB	view
4k	216.3	22.2	17.3 GB	view
8k	198.3	21.9	18.3 GB	current
16k	201.9	20.3	19.8 GB	view
32k	170.2	15.1	22.8 GB	view