← Back to community benchmarks

Qwen3.6-35B-A3B-UD

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

Performance

8k

tokens

1,407

PP tok/s

79.7

TG tok/s

5822

TTFT (ms)

21.9

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 8,192

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	current
16k	2,911	34.6	23.1 GB	view
32k	2,646	33.9	23.7 GB	view
64k	2,176	32.4	25.6 GB	view