← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 128 GB · 4bit · 2026-07-23

Performance

32k

tokens

592.7

PP tok/s

38.1

TG tok/s

55283

TTFT (ms)

22.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.3

macOS macOS 26.5.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	730.7	68.4	21.2 GB	view
8k	778.1	67.3	21.4 GB	view
16k	772.9	67.1	21.7 GB	view
32k	592.7	38.1	22.2 GB	current
64k	288.6	17.1	23.3 GB	view
128k	230.5	14.7	25.6 GB	view