← Back to community benchmarks

Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved

M4 Max (32c) · 36 GB · 4bit · 2026-05-06

Performance

8k

tokens

183.1

PP tok/s

20.3

TG tok/s

44744

TTFT (ms)

18.3

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	186.9	21.6	15.8 GB	view
4k	190.9	20.7	17.3 GB	view
8k	183.1	20.3	18.3 GB	current