LocateAnything Models

Browse and run open-source AI models locally on your own hardware — no API keys, no cloud, no usage limits. Fully private, works offline, and free forever.

LocateAnything running in Atomic Chat
Qwen3.6 27B MTP
27B
No models found
Reasoning
Code
Multilingual
Web
Vision
Thinking
Tools
Audio
Visuals
Embedding
LocateAnything-3B

NVIDIA's 3.8B visual grounding model: name an object in plain English and it returns exact bounding boxes or points, from GUI buttons to cluttered street scenes.

Thinking
Vision
Reasoning
Code