← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 64 GB · 4bit · 2026-05-19

Performance

4k

tokens

900.2

PP tok/s

31.2

TG tok/s

4550

TTFT (ms)

17.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	781.1	31.8	16.4 GB	view
4k	900.2	31.2	17.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	31.8	1.00×
2×	58.0	1.82×
4×	72.9	2.29×