← Back to community benchmarks

Qwen3.6-27B-PARO-MTP

M1 Max (32c) · 64 GB · 4bit · 2026-05-13

Performance

16k

tokens

135.9

PP tok/s

17.1

TG tok/s

120567

TTFT (ms)

19.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	144.9	19.4	15.5 GB	view
4k	143.4	18.9	16.7 GB	view
8k	138.7	18.1	17.8 GB	view
16k	135.9	17.1	19.3 GB	current