← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (32c) · 36 GB · 4bit · 2026-05-12

Performance

4k

tokens

198.7

PP tok/s

20.4

TG tok/s

20612

TTFT (ms)

17.9

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

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	188.5	20.8	16.4 GB	view
4k	198.7	20.4	17.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	20.8	1.00×
2×	38.8	1.87×
4×	45.0	2.16×