← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M4 Max (40c) · 64 GB · 6bit · 2026-05-20

Performance

8k

tokens

239.9

PP tok/s

27.0

TG tok/s

34141

TTFT (ms)

25.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	231.6	24.8	23.0 GB	view
4k	240.6	27.7	24.4 GB	view
8k	239.9	27.0	25.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	24.8	1.00×
2×	34.0	1.37×
4×	36.8	1.48×