← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-06-22

Performance

16k

tokens

236.7

PP tok/s

25.6

TG tok/s

69229

TTFT (ms)

21.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	237.1	28.4	17.4 GB	view
4k	245.2	27.5	18.8 GB	view
8k	243.0	26.9	19.8 GB	view
16k	236.7	25.6	21.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.4	1.00×
2×	48.0	1.69×
4×	55.1	1.94×