← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-26

Performance

16k

tokens

2,280

PP tok/s

59.1

TG tok/s

7185

TTFT (ms)

102.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.20

macOS macOS 26.3.1

Context 16,384