← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 64 GB · 4bit · 2026-07-22

Performance

16k

tokens

1,598

PP tok/s

100.8

TG tok/s

10256

TTFT (ms)

20.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,872	115.4	20.1 GB	view
16k	1,598	100.8	20.3 GB	current
64k	984.2	76.3	21.5 GB	view