← Back to community benchmarks

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

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

Performance

4k

tokens

190.9

PP tok/s

20.7

TG tok/s

21458

TTFT (ms)

17.3

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 4,096

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	current
8k	183.1	20.3	18.3 GB	view