← Back to community benchmarks

Qwen3.6-27B

M1 Max (32c) · 32 GB · 4bit · 2026-04-25

Performance

16k

tokens

87.2

PP tok/s

16.2

TG tok/s

187977

TTFT (ms)

19.1

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	84.7	19.2	15.8 GB	view
4k	87.3	18.6	17.3 GB	view
8k	88.8	17.8	17.9 GB	view
16k	87.2	16.2	19.1 GB	current