← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (30c) · 36 GB · 4bit · 2026-07-13

Performance

64k

tokens

614.7

PP tok/s

45.6

TG tok/s

106621

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.5.0

macOS macOS 26.3.1

Context 65,536