← Back to community benchmarks

Qwen3.6-35B-A3B-PARO

M5 Max (40c) · 64 GB · 4bit · 2026-07-20

Performance

64k

tokens

2,206

PP tok/s

59.5

TG tok/s

29713

TTFT (ms)

24.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536