← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (32c) · 36 GB · 4bit · 2026-04-16

Performance

64k

tokens

864.8

PP tok/s

40.5

TG tok/s

75778

TTFT (ms)

25.0

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 65,536