← Back to community benchmarks

Qwen3.6-35B-A3B

M2 Max (38c) · 96 GB · 6bit · 2026-04-17

Performance

8k

tokens

737.4

PP tok/s

63.3

TG tok/s

11109

TTFT (ms)

28.4

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	600.1	69.8	27.3 GB	view
4k	734.0	66.4	28.1 GB	view
8k	737.4	63.3	28.4 GB	current