AIXDAabout 1 hour ago
Tablet runs desktop-class LLMs via Lemonade router
1 min read
The Asus ROG Flow Z13 Ludens Edition, with a Ryzen AI Max+ 395 and 128 GB unified memory, loads a 120B model in 27.6 seconds and generates at 52.03 tokens per second. Lemonade's router sends heavy prompts to the 120B tier and smaller tasks to lighter models.
Level
Hype check
Tap to vote and see what everyone thinks.
