← Back to community benchmarks

Qwen3.6-35B-A3B

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

Performance

1k

tokens

1,417

PP tok/s

330.0

TG tok/s

723

TTFT (ms)

36.7

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 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,417	330.0	36.7 GB	current
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	view
32k	1,375	63.1	38.5 GB	view