NVIDIA ships Nemotron 3.5 Bolt E4B, a 4GB open model for robots and on-device agents
AIFlow_ML · x · 2026-10-24
NVIDIA released Nemotron 3.5 Bolt E4B, an open 4GB small language model built on Gemma 4 E4B with Nemotron post-training, optimized for conversational agents on Jetson, GeForce RTX and DGX Spark — demoed running beside a vision model on a Jetson Orin Nano driving a Reachy Mini robot.
- 40% higher average quality on agent benchmarks vs its predecessor, up to 80% fewer output tokens than peers
- Multi-turn tool use, speech-ready conversational mode, configurable/cappable reasoning, 64k context, 35 languages
- Aimed at voice/device assistants, interactive characters and robotic/IoT interfaces with local, responsive inference
Related event: NVIDIA open-sources 4GB edge model Nemotron 3.5 Bolt E4B(11 posts)→
More from Embodied
- DeXplicit Makes Physical State Explicit in Dexterous Manipulation World Models — liuziwei7 · 2026-10-24
- Asimov 1 ships as a DIY kit; German engineer set 3-day assembly record — IgorCarron · 2026-10-24
- Tiny biped duck robot microduck goes viral with 10.6k GitHub stars — pollen-robotics · 2026-10-24
- A wearable pendant that orchestrates Claude, GPT, Gemini and more voice-first — EricBuess · 2026-10-24
- Boston Dynamics employees petition to cancel $1.3M Spot robot sale to ICE — VectorWireAI · 2026-10-24
- Tesla starts production of Optimus humanoid robots, targets 20,000 units per week — LexiLove · 2026-10-24