← Back to community benchmarks

Qwen3.5-122B-A10B

M4 Max (40c) · 128 GB · 4bit · 2026-03-20

Performance

16k

tokens

549.8

PP tok/s

38.2

TG tok/s

29801

TTFT (ms)

69.7

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	598.1	53.2	67.9 GB	view
8k	585.2	51.3	68.5 GB	view
16k	549.8	38.2	69.7 GB	current
32k	483.4	27.1	72.1 GB	view
64k	378.3	16.3	77.0 GB	view