← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (30c) · 36 GB · 4bit · 2026-05-20

Performance

1k

tokens

158.5

PP tok/s

16.9

TG tok/s

6459

TTFT (ms)

16.4

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	16.9	1.00×
2×	27.3	1.62×
4×	33.1	1.96×