← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M4 Max (40c) · 48 GB · 4bit · 2026-04-24

Performance

1k

tokens

1,389

PP tok/s

112.7

TG tok/s

737

TTFT (ms)

19.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024