← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-30

Performance

32k

tokens

1,104

PP tok/s

42.1

TG tok/s

29670

TTFT (ms)

71.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.23

macOS macOS 26.4

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	1,554	57.4	67.7 GB	view
16k	1,352	51.1	68.9 GB	view
32k	1,104	42.1	71.2 GB	current