← Back to community benchmarks

Qwen3.6-35B-A3B-q4

M4 Max (40c) · 64 GB · 4bit · 2026-04-16

Performance

32k

tokens

3,186

PP tok/s

44.8

TG tok/s

10285

TTFT (ms)

22.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,441	213.9	20.6 GB	view
4k	691.7	99.5	20.8 GB	view
8k	1,600	94.1	21.1 GB	view
16k	3,244	46.0	22.3 GB	view
32k	3,186	44.8	22.9 GB	current
64k	2,432	43.9	24.8 GB	view
128k	1,764	39.3	27.4 GB	view