← Back to community benchmarks

Qwen3.5-122B-A10B-Text-mxfp4

M3 Max (30c) · 96 GB · 4bit · 2026-03-23

Performance

4k

tokens

373.1

PP tok/s

35.3

TG tok/s

10977

TTFT (ms)

63.5

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 96 GB

GPU Cores 30

Software

oMLX v0.2.20

macOS macOS 26.3.1

Context 4,096