← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 64 GB · 4bit · 2026-05-10

Performance

1k

tokens

752.3

PP tok/s

43.5

TG tok/s

1361

TTFT (ms)

16.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	43.5	1.00×
2×	47.8	1.10×
4×	51.4	1.18×