← Back to community benchmarks

Qwen3.6-27B-oQ4-fp16-mtp

M1 Max (24c) · 64 GB · 4bit · 2026-05-23

Performance

8k

tokens

93.9

PP tok/s

14.6

TG tok/s

87264

TTFT (ms)

18.8

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	108.2	15.8	16.7 GB	view
4k	97.0	15.0	18.2 GB	view
8k	93.9	14.6	18.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.8	1.00×
2×	17.3	1.09×
4×	19.9	1.26×
8×	68.7	4.35×