← Back to community benchmarks

Qwen3.5-122B-A10B

M4 Max (40c) · 128 GB · 4bit · 2026-03-19

Performance

16k

tokens

519.9

PP tok/s

40.0

TG tok/s

31512

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	594.7	50.7	67.9 GB	view
16k	519.9	40.0	69.7 GB	current
32k	454.9	32.8	72.1 GB	view
64k	346.1	23.5	77.0 GB	view