← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 64 GB · 4bit · 2026-04-28

Performance

16k

tokens

1,554

PP tok/s

88.0

TG tok/s

10541

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,448	404.8	20.6 GB	view
4k	944.3	107.0	20.0 GB	view
8k	1,674	99.4	20.4 GB	view
16k	1,554	88.0	21.0 GB	current
32k	1,292	70.4	22.4 GB	view
64k	966.6	36.5	25.0 GB	view
128k	587.3	21.8	30.4 GB	view