← Back to community benchmarks

Qwen3.5-122B-A10B

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

Performance

8k

tokens

236.9

PP tok/s

33.1

TG tok/s

34574

TTFT (ms)

67.0

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 8,192

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	current
32k	212.3	20.3	69.1 GB	view
64k	182.6	13.4	71.9 GB	view