← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 4bit · 2026-06-07

Performance

64k

tokens

2,033

PP tok/s

79.5

TG tok/s

32232

TTFT (ms)

25.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.2rc1

macOS macOS 26.5.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	3,183	114.7	20.0 GB	view
16k	3,534	107.4	21.0 GB	view
64k	2,033	79.5	25.0 GB	current