NVIDIA Nemotron 3.5 Lightning Arrives on Ollama, Runs Fully Locally
Original title:NVIDIA Nemotron 3.5 Lightning
AI summary
NVIDIA Nemotron 3.5 Lightning is now available on Ollama and can run entirely on local devices. The model is a 30B total-parameter hybrid MoE open model with only 3B activated per token, aimed at always-on agent tasks, supporting up to 1M token context, achieving up to 4x throughput gains via MTP, DFlash or DSpark speculative decoding, and completing tasks 30% faster than comparable open-source models.
Key Takeaways
- NVIDIA Nemotron 3.
- 5 Lightning is now available on Ollama and can run entirely on local devices.
- The model is a 30B total-parameter hybrid MoE open model with only 3B activated per token,aimed at…
Quick Facts
- Published
- Updated
- Source
- Ollama:Blog(RSS)
- Category
- Products & Apps
- AI score
- 68
原文给出了参数结构、上下文长度、吞吐数据和本地运行入口,读者可以据此判断它是否适合长期运行的本地智能体工作流。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: NVIDIA Nemotron 3.5 Lightning Arrives on Ollama, Runs Fully Locally. August 11, 2026. https://new.nat6.net/en/news/nnyomlhxd0zfh6q189nlstm1z/