← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 48 GB · 4bit · 2026-03-11

Performance

8k

tokens

1,712

PP tok/s

103.8

TG tok/s

4785

TTFT (ms)

20.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.2.8

macOS macOS 26.3.1

Context 8,192