← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Pro (16c) · 64 GB · 4bit · 2026-04-23

Performance

32k

tokens

1,327

PP tok/s

24.3

TG tok/s

24696

TTFT (ms)

22.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.4

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	347.1	65.6	20.4 GB	view
8k	696.1	72.4	20.8 GB	view
16k	1,501	25.4	21.9 GB	view
32k	1,327	24.3	22.6 GB	current
64k	1,101	23.5	24.4 GB	view
128k	802.1	21.7	27.1 GB	view