NVIDIA releases open-source Nemotron 3.5 Bolt E4B 4GB model
The story so far
NVIDIA releases Nemotron 3.5 Bolt E4B 4GB, an open-source small language model designed for local fast dialogue agents, supporting voice assistants, game NPCs, and robot interfaces. The model is based on Google Gemma 4 E4B and is only post-trained through reinforcement learning, with a total of 8B parameters, 4B effective parameters, and a context window of 64K.
AI-written from the reports · Updated 26 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- MarkTechPostNVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots
NVIDIA releases Nemotron 3.5 Bolt E4B 4GB, an open-source small language model designed for local fast dialogue agents, supporting voice assistants, game NPCs, and robot interfaces. The model is based on Google Gemma 4 E4B and is only post-trained through reinforcement learning, with a total of 8B parameters, 4B effective parameters, and a context window of 64K.