← Back to community benchmarks

Qwen3.6-27B-uncensored-heretic-v2-oQ8-fp16-mtp

M1 Max (24c) · 64 GB · 8bit · 2026-05-24

Performance

64k

tokens

94.6

PP tok/s

10.2

TG tok/s

692708

TTFT (ms)

41.8

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9

macOS macOS 26.5

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	114.7	14.3	28.8 GB	view
4k	117.3	13.7	30.3 GB	view
8k	116.4	13.8	31.3 GB	view
16k	113.8	12.9	32.8 GB	view
32k	107.8	12.2	35.8 GB	view
64k	94.6	10.2	41.8 GB	current