← Back to community benchmarks

Qwen3.6-35B-A3B-PARO

M3 Max (40c) · 64 GB · 4bit · 2026-06-07

Performance

64k

tokens

778.7

PP tok/s

46.1

TG tok/s

84162

TTFT (ms)

24.3

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.2rc1

macOS macOS 26.4.1

Context 65,536