← Back to community benchmarks

Qwen3.5-122B-A10B

M2 Max (38c) · 96 GB · 4bit · 2026-03-14

Performance

32k

tokens

212.3

PP tok/s

20.3

TG tok/s

154380

TTFT (ms)

69.1

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	239.3	36.8	66.7 GB	view
8k	236.9	33.1	67.0 GB	view
32k	212.3	20.3	69.1 GB	current
64k	182.6	13.4	71.9 GB	view