← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-05-17

Performance

1k

tokens

198.7

PP tok/s

34.6

TG tok/s

5152

TTFT (ms)

16.7

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	198.7	34.6	16.7 GB	current
4k	211.9	36.1	18.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	34.6	1.00×
2×	39.6	1.14×
4×	44.8	1.29×