← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (32c) · 36 GB · 4bit · 2026-05-05

Performance

16k

tokens

2,911

PP tok/s

34.6

TG tok/s

5628

TTFT (ms)

23.1

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,421	85.6	21.6 GB	view
8k	1,407	79.7	21.9 GB	view
16k	2,911	34.6	23.1 GB	current
32k	2,646	33.9	23.7 GB	view
64k	2,176	32.4	25.6 GB	view