← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Max (40c) · 128 GB · 4bit · 2026-05-02

Performance

8k

tokens

1,444

PP tok/s

73.6

TG tok/s

5674

TTFT (ms)

21.5

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 15.7.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,247	154.4	21.7 GB	view
4k	742.9	79.5	21.2 GB	view
8k	1,444	73.6	21.5 GB	current