NVIDIA releases Nemotron 3.5 Bolt E4B, a 4GB open model for on-device conversational agents
NVIDIAAI · x · 2026-10-23
NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B for local conversational agents on voice/device assistants, interactive characters, and robots.
Key points:
- 40% higher average quality vs the prior model on conversational agent benchmarks, and up to 80% fewer output tokens than peers, fitting in 4GB for target workloads
- Multi-turn tool use (with async tool-call integration guidance), a concise speech-ready conversational mode, configurable reasoning with latency caps, 64k context, and 35 languages
- Runs locally on GeForce RTX, Jetson, RTX Spark, and DGX Spark; a Reachy Mini demo pairs Bolt for conversation with NVIDIA Cosmos for vision, all on a Jetson Orin Nano 8GB
Related event: NVIDIA Releases Nemotron 3.5 Bolt E4B for On-Device Agents(2 posts)→
More from Embodied
- A $2,490 humanoid and a hosted robot-model API land in the same week — AIFlow_ML · 2026-10-24
- Microduck: why this cute robot toy matters more than it looks — TinfoilTricorn · 2026-10-23
- AGIBOT's A3 Ultra humanoid robot demonstrates roller-skating mobility — TinfoilTricorn · 2026-10-23
- Xaira details X-Automate: X-Scientist, X-Bot and mobile robots link protein design to testing — BoWang87 · 2026-10-23
- Xaira's first 7-day lab deployment: 18 plates, 97.2% utilization, humans still needed — BoWang87 · 2026-10-23
- Xaira launches X-Automate, pairing agentic AI with robots to break the wet-lab bottleneck — BoWang87 · 2026-10-23