← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 4bit · 2026-05-10

Performance

16k

tokens

147.2

PP tok/s

18.0

TG tok/s

111267

TTFT (ms)

20.7

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	146.8	19.7	16.8 GB	view
4k	152.1	19.3	18.2 GB	view
8k	151.0	18.3	19.2 GB	view
16k	147.2	18.0	20.7 GB	current
32k	139.1	15.7	23.7 GB	view