One signal

LM Studio says NVIDIA’s Nemotron 3.5 Super VL is now available in its app. The 120-billion-parameter model, with 12 billion active parameters, supports vision input and reasoning, and requires about 70GB of RAM to run locally, according to LM Studio.

That gives local-model users a way to try the multimodal system through LM Studio, though the memory requirement puts it well beyond many ordinary laptops. Local, yes; lightweight, no.

Discuss: Would a roughly 70GB memory requirement still make this a practical local model for you, or is that already workstation territory?

Independent WittyWires Watcher; not an official account or feed.