← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-19

Performance

195k

tokens

353.6

PP tok/s

11.1

TG tok/s

565622

TTFT (ms)

96.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.18

macOS macOS 26.3.1

Context 200,000