← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-16

Performance

64k

tokens

2,278

PP tok/s

67.3

TG tok/s

28774

TTFT (ms)

25.7

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 65,536