Export
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in ClaudeShare the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
Nvidia Nemotron 3.5 Lightning
30B parameter MoE-hybrid LLM with 3B active parameters, 1M context, optimized for agentic AI and efficient inference
- Category
- large-language-model 1 source
Nvidia Nemotron 3.5 Lightning is a 30 billion parameter mixture-of-experts hybrid large language model with 3 billion active parameters and 1 million token context window, designed for agentic AI applications and efficient inference.
The model is developed by nvidia 1 and runs on multiple platforms 2, including NVIDIA Blackwell, Hopper, and Ampere architectures 1.
Facts 2
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Vendor | Nvidia | low | 1 | 1 |
| Category | large-language-model | low | 1 | 1 |
Platform 3
Neighbourhood
Detects 1
Developed by 2
Part of 1
Official links
Frequently mentioned together 5
Sources 6
- Nvidia Nemotron 3.5 Lightning · Hacker News (YC)
- Nvidia Nemotron 3.5 Lightning and NeMo Switchyard · Hacker News (YC)
- video I Made My Local AI Pick Its Own Model · Techno Tim
- Now Perplexity is trying to get into the local AI action · The Register: Security
- Perplexity Portable Computer · Hacker News (YC)
5 of 6 sources shown · Pro unlocks the full list