by PositronUS
Provide production inference for models up to 500 billion parameters with standard APIs.
In production. Supports models up to 500 billion parameters.
Checked 11 Oct0 updates this week
Atlas exposes standard OpenAI API endpoints, letting customers use existing code without modification.
| Spec | Atlas |
|---|---|
| Maximum model size | 500 billion parametersR (reported) |
R reported by the company
Positron
Atlas, Asimov inference chip, Titan system
Positron designs hardware and software for AI inference, reducing cost and power. Founded in 2023, it develops Atlas (in production) and Asimov chip (2027). September 2026 raised $875M at $5B.
