← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M5 Max (40c) · 48 GB · 4bit · 2026-06-04

Performance

16k

tokens

3,881

PP tok/s

100.9

TG tok/s

4222

TTFT (ms)

22.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.4.1

macOS macOS 26.5.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	3,410	106.7	20.8 GB	view
8k	3,857	102.2	21.5 GB	view
16k	3,881	100.9	22.2 GB	current