← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 64 GB · 4bit · 2026-05-11

Performance

16k

tokens

1,311

PP tok/s

85.8

TG tok/s

12495

TTFT (ms)

22.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

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
1k	1,310	98.2	20.4 GB	view
4k	1,253	96.5	21.2 GB	view
8k	1,375	92.2	21.7 GB	view
16k	1,311	85.8	22.4 GB	current
32k	1,137	77.8	23.9 GB	view