Models & Labs
NVIDIA Nemotron 3.5 Lightning Launches for Local AI Agents
Ollama Bloghigh confidence
Why it matters
- →Enables local execution of AI agents, enhancing privacy and data security.
- →Offers significant performance improvements with 4x higher throughput.
- →Provides a customizable platform for developers to tailor AI solutions to specific tasks.
NVIDIA has released the Nemotron 3.5 Lightning, a 30 billion parameter model optimized for running AI agents locally on devices. This model is designed to handle complex tasks such as tool calling and multi-step workflows, with only 3 billion active parameters per token. It offers significant improvements in throughput and task completion time compared to other models of similar size. By running locally, Nemotron 3.5 Lightning ensures user data remains private, making it ideal for applications like personal assistants and coding sub-agents.
Read originalThe story around this
TopicNvidia Product And Business UpdatesCooling
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1NVIDIA Launches Nemotron 3 Nano Omni Model
NVIDIA Blog · April 28, 2026 · Same story
- 2NVIDIA Launches Nemotron 3 Nano Omni
Matt Wolfe · May 1, 2026 · Same story
- 3Nvidia Unveils AI Agent-Centric Tech at COMPUTEX
The Rundown AI · June 2, 2026 · Same story
- 4NVIDIA Launches Nemotron 3 Ultra Model
Ollama Blog · June 4, 2026 · Same story
- 5NVIDIA Unveils Nemotron 3 Ultra Model
Sam Witteveen · June 4, 2026 · Same story
- 6NVIDIA Unveils Nemotron 3 Ultra for AI Agents
Matt Wolfe · June 5, 2026 · Same story
- 7NVIDIA Nemotron 3 Ultra Boosts AI Agent Performance
NVIDIA Blog · July 8, 2026 · Same story
- 8NVIDIA's Nemotron Enhances AI with Open Synthetic Data
Hugging Face Blog · July 8, 2026 · Same story
What happened next
- 9NVIDIA Jetson Orin Nano 2 targets edge AI for robots
AI News · August 26, 2026 · Related
- 10Nvidia Unveils AI-Powered RTX Spark PCs
WIRED AI · September 3, 2026 · Related
- 11NVIDIA Automates Supply Chain with AI Tools
AI News · September 11, 2026 · Related
- 12NVIDIA Nemotron 3 Diarization Model Released
Sam Witteveen · September 23, 2026 · Related
- 13Nvidia Launches Open-Source AI Agent Security Platform
WIRED AI · September 28, 2026 · Related
Follow this story
Open the full story →NVIDIA Nemotron 3.5 Lightning Launches for Local AI Agents
6 developments
- Aug 11 · Ollama Blog
NVIDIA Nemotron 3.5 Lightning Launches for Local AI Agents (This article) - Aug 11 · NVIDIA Blog
NVIDIA Unveils Nemotron 3.5 Lightning and NeMo Switchyard - Aug 11 · Sam Witteveen
NVIDIA Launches NeMo Switchyard for AI Agents↳ NeMo Switchyard is an open-source library that acts as a router to select the best model for each task, optimizing efficiency and token usag - Aug 11 · Sam Witteveen
NVIDIA Unveils Nemotron Lightning Model - Aug 14 · Matt Wolfe
NVIDIA Launches Nemotron 3.5 Lightning↳ The model is designed for specialized task execution. - Aug 14 · Lev Selector
NVIDIA Unveils Nemotron 3.5 Lightning
More in Models & Labs
Models & Labscoding
vLLM v0.31.0: SM100 defaults and fast restarts
vLLM is quietly becoming the definitive runtime for NVIDIA's latest hardware, making NVFP4 compressed KV caches the default for DeepSeek-V4.1-Flash on SM100 GPUs. This isn't just a performance tweak; it fundamentally changes how enterprise inference scales by keeping post-quantized weights resident in GPU memory across engine restarts via the new preload daemon. The release also hardens speculative decoding with Model Runner V2, fixing OOMs that previously plagued wide expert deployments. For builders, this means lower latency and higher throughput on next-gen hardware without manual configuration overhead.
vLLM Releases
Models & Labsmodels
llama.cpp v0.6.0 adds decision model API and Apple Silicon speedups
This release shifts llama.cpp from a pure text engine to a multimodal inference runtime capable of handling 'decision models' like Clef and GLM-5.3-Flash. The new /v1/systemone server endpoint standardizes how these non-autoregressive models are queried, while the extended batch API allows mixed token and embedding inputs for complex architectures. Apple Silicon users get a tangible performance boost with new Metal MMA kernels that accelerate speculative decoding by up to 3x. It’s a significant step toward supporting the next generation of hybrid reasoning models locally.
llama.cpp Releases
© Hugging Face BlogModels & Labsmodels
Falcon-Emirati-7B targets dialect nuance
Most Arabic models treat the language as a monolith, missing the cultural and linguistic depth of specific dialects. Falcon-Emirati-7B closes this gap by fine-tuning on native Emirati text, synthetic data constrained by strict glossaries, and cultural heritage knowledge. It tops the new Alyah benchmark with 84.83%, proving that scale alone doesn't buy dialect competence. This release underscores a critical shift: true multilingual capability requires targeted adaptation, not just larger parameter counts.
Hugging Face Blog