← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4-mtp

M2 Max (30c) · 64 GB · 4bit · 2026-07-12

Performance

16k

tokens

394.9

PP tok/s

40.3

TG tok/s

41485

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	445.4	51.7	20.6 GB	view
16k	394.9	40.3	21.0 GB	current
64k	274.7	43.8	22.3 GB	view