← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 4bit · 2026-03-24

Performance

16k

tokens

490.8

PP tok/s

42.8

TG tok/s

33382

TTFT (ms)

65.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.20

macOS macOS 26.3

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	490.8	42.8	65.3 GB	current
32k	412.9	37.2	67.7 GB	view
64k	332.2	28.6	72.6 GB	view