← Back to community benchmarks

Qwen3.5-122B-A10B

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

Performance

64k

tokens

914.5

PP tok/s

31.9

TG tok/s

71663

TTFT (ms)

76.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.1

macOS macOS 26.4

Context 65,536

Performance by Context Length

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