NVIDIA releases Nemotron 3.5 Bolt E4B, a 4GB small model for local assistants
A compact open model aimed at assistants, characters and robots.
NVIDIA AI (@NVIDIAAI) announced Nemotron 3.5 Bolt E4B on Friday, calling it its newest small open model. The post describes a 4GB model for local assistants, interactive characters and robots that hold a conversation. It drew about 1,100 likes.
At 4GB, a model can run on many laptops and edge devices without a data centre. The post does not include benchmark numbers or licence terms.
Why it mattersSmall models that run locally are how voice assistants and robots can respond quickly without sending everything to the cloud. Check the model card for details.
