3Yesterday 8:00 AM · 20h ago · 1 article · 1 post · 2 sources · development 3 of 4
NVIDIA released new software features, performance optimizations, and the Nemotron 3.5 Bolt 74B-A9B model (24GB, available Oct. 15) purpose-built for running local agents on RTX Spark. Updates include OpenShell and MXC security sandboxing, NVIDIA Switchyard for intelligent local-to-cloud model routing, and simplified agent setup across GitHub Copilot, Hermes Agent, OpenClaw, Perplexity, Pi, and WorkBuddy.
blogs.nvidia.com
“NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB, available Thursday, Oct. 15, is a new LLM purpose-built for running local agents on RTX Spark.”
NVIDIA
NVIDIAHardware manufacturer and software providerMicrosoftCo-partner in RTX Spark launchJensen HuangNVIDIA CEO
The whole story articlespoststhe bright band is this development · numbered dots are the others · click one to jump