Nvidia Releases Compact Nemotron 3.5 Bolt Model
Today features only one qualified news item. Nvidia launched a compact model tailored for local conversational agents.
Nvidia Launches Nemotron 3.5 Bolt for On-Device Agents
On October 23, 2026, Nvidia introduced Nemotron 3.5 Bolt E4B 4GB. The open small language model builds on Gemma 4 E4B and includes post-training optimized for conversational agents running on local hardware. It fits into a memory footprint of roughly 4 gigabytes. According to Nvidia, the model scores about 40 percent higher on key agent benchmarks than the previous Nano 4B model. In reasoning tests, it generates up to 80 percent fewer tokens, lowering decoding costs and speeding up responses. The system supports multi-turn tool calling and covers 35 languages. It runs on platforms like GeForce RTX, RTX Spark, and Jetson devices.
What it means: Small models allow responsive assistants to run directly on consumer hardware without remote servers. This lowers cloud computing bills and keeps sensitive data on the device.
Example: A smart home hub could understand spoken multi-step device controls locally, without sending sensitive room audio to an external cloud.
- NVIDIA Nemotron 3.5 Bolt E4B 4GB - NVIDIA Nemotron · 23 October 2026