← Back to community benchmarks

Qwen3.5-9B

M3 Max (40c) · 128 GB · 4bit · 2026-07-23

Performance

64k

tokens

506.3

PP tok/s

25.6

TG tok/s

129431

TTFT (ms)

8.3

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536