← Back to community benchmarks

Qwen3.6-35B-A3B

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

Performance

8k

tokens

696.1

PP tok/s

72.4

TG tok/s

11769

TTFT (ms)

20.8

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.4

Context 8,192

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	current
16k	1,501	25.4	21.9 GB	view
32k	1,327	24.3	22.6 GB	view
64k	1,101	23.5	24.4 GB	view
128k	802.1	21.7	27.1 GB	view