← Back to community benchmarks

Qwen3.6-35B-A3B-oQ3.5

M1 Max (24c) · 32 GB · 3bit · 2026-05-12

Performance

32k

tokens

628.7

PP tok/s

47.9

TG tok/s

52122

TTFT (ms)

20.2

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 32,768