← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 4bit · 2026-04-05

Performance

16k

tokens

503.3

PP tok/s

33.5

TG tok/s

32555

TTFT (ms)

65.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.4

macOS macOS 15.7.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	469.9	53.2	62.0 GB	view
4k	539.0	51.5	63.4 GB	view
8k	533.1	46.4	64.0 GB	view
16k	503.3	33.5	65.1 GB	current
32k	446.6	30.2	67.5 GB	view
64k	350.9	20.3	72.4 GB	view
128k	238.2	0.5	82.0 GB	view