NVIDIA releases Nemotron 3.5 Bolt E4B for edge devices
NVIDIA released Nemotron 3.5 Bolt E4B as a small open model for local assistants, interactive characters, robots, voice interfaces, and embedded devices. The model card says the 4GB version is post-trained from Gemma-4-E4B-it and improves multi-turn tool use, instruction following, and input grounding, while UnslothAI reports that it supports vision and can run locally with 6GB of RAM. NVIDIA AI lists the 4GB model as available, and the model is licensed for commercial or non-commercial use.
The release adds an open model focused on low-memory local inference and tool use on phones, robots, and other edge devices.
NVIDIA releases Nemotron-3.5-Bolt-E4B, a new model that runs locally on 6GB RAM. 💚 Bolt-E4B can run on edge devices like phones and delivers top-tier performance for its size. Trained on Gemma 4, it supports vision. GGUF: https://huggingface.co/unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF Guide: https://unsloth.ai/docs/models/nemotron-3.5-bolt
NVIDIA AI: Available now: NVIDIA Nemotron 3.5 Bolt E4B 4GB ⚡️ Our newest small open model is built for local assistants, interactive characters and robots that can carry on a conversation and use tools to get things done. Watch Reachy Mini chat and move, with Bolt handling conversation
#NVIDIA#NVIDIA Nemotron 3.5 Bolt E4B#Gemma 4#Gemma-4-E4B-it#DFlash drafter