← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (30c) · 36 GB · 4bit · 2026-05-11

Performance

1k

tokens

159.1

PP tok/s

23.4

TG tok/s

6436

TTFT (ms)

16.8

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	159.1	23.4	16.8 GB	current
4k	156.5	23.9	18.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.4	1.00×
2×	30.2	1.29×
4×	34.9	1.49×