← Back to community benchmarks

Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-oQ4

M5 (10c) · 32 GB · 4bit · 2026-06-05

Performance

8k

tokens

112.8

PP tok/s

6.3

TG tok/s

72599

TTFT (ms)

18.4

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.4.1

macOS macOS 26.5.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	171.1	12.4	16.1 GB	view
4k	175.1	12.2	17.0 GB	view
8k	112.8	6.3	18.4 GB	current