← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4-mtp

M2 Pro (16c) · 32 GB · 4bit · 2026-05-18

Performance

16k

tokens

304.4

PP tok/s

32.2

TG tok/s

53822

TTFT (ms)

22.1

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 16,384