← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-04-03

Performance

4k

tokens

1,390

PP tok/s

63.8

TG tok/s

2946

TTFT (ms)

67.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.1

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,390	63.8	67.0 GB	current
64k	914.5	31.9	76.1 GB	view
195k	406.9	14.5	95.9 GB	view