← Back to community benchmarks

Qwen3.6-27B

M1 Pro (16c) · 32 GB · 4bit · 2026-06-17

Performance

4k

tokens

42.5

PP tok/s

10.0

TG tok/s

96291

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.4.4rc2

macOS macOS 27.0

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	41.7	10.2	15.8 GB	view
4k	42.5	10.0	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	10.2	1.00×
2×	11.3	1.11×
4×	11.6	1.14×