← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-05-22

Performance

8k

tokens

222.2

PP tok/s

37.3

TG tok/s

36862

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	239.3	39.4	16.7 GB	view
4k	241.4	39.2	18.2 GB	view
8k	222.2	37.3	19.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	39.4	1.00×
2×	47.1	1.20×
4×	53.4	1.36×