← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-04-27

Performance

16k

tokens

1,600

PP tok/s

73.4

TG tok/s

10237

TTFT (ms)

37.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8.dev3

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,417	330.0	36.7 GB	view
4k	1,291	274.3	37.8 GB	view
8k	1,137	80.6	36.5 GB	view
16k	1,600	73.4	37.1 GB	current
32k	1,375	63.1	38.5 GB	view