← Back to community benchmarks

Qwen3.6-27B

M3 Max (40c) · 128 GB · fp16 · 2026-05-01

Performance

1k

tokens

223.9

PP tok/s

7.2

TG tok/s

4574

TTFT (ms)

51.7

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 15.4.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	7.2	1.00×
2×	6.9	0.96×
4×	13.4	1.86×