← Back to community benchmarks

Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved

M2 Max (38c) · 96 GB · 8bit · 2026-07-17

Performance

4k

tokens

726.2

PP tok/s

55.4

TG tok/s

5641

TTFT (ms)

36.1

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	726.2	55.4	36.1 GB	current
16k	528.3	48.8	36.6 GB	view
64k	335.0	33.1	37.8 GB	view