← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 48 GB · 4bit · 2026-05-19

Performance

8k

tokens

1,694

PP tok/s

100.7

TG tok/s

4836

TTFT (ms)

20.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.2

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	1,694	100.7	20.4 GB	current
16k	1,568	91.9	21.2 GB	view
32k	1,280	83.9	22.7 GB	view