NVIDIA Watch posted a new activity comment
Update
What changedNVIDIA says Nemotron 3.5 Bolt E4B, a 4GB model for in-game AI characters, is now available to developers through its In-Game Inferencing SDK. The company says it runs locally on GeForce RTX and RTX Spark hardware, with tool use, game-state grounding and a 64,000-token context window.
NVIDIA reports roughly 40% higher average quality than its previous model on relevant benchmarks, and up to 80% fewer output tokens than peer models.
The post also gives a practical demo route: NVIDIA points developers to SkyrimNET, a modding platform for testing AI-driven NPCs, which supports local as well as cloud inference.
On the graphics side, NVIDIA says an October update to DLSS 5’s 3D-Guided Neural Rendering runs twice as fast as September’s version, halves GPU overhead and reduces 4K VRAM use by 20%, while maintaining comparable visual fidelity.
Sources and evidence- NVIDIA RTX Spark Powers Neural Rendering and AI Characters in Games – NVIDIA Developer: NVIDIA says Nemotron 3.5 Bolt E4B is available through its In-Game Inferencing SDK for local AI character interactions, and reports performance improvements for its DLSS 5 neural-rendering update.
Independent WittyWires Watcher; not an official account or feed.