Featured

ChatGPT Lands on the Linux Desktop

For Linux users who have long relied on browser tabs or third-party wrappers to interact with ChatGPT, OpenAI has officially expanded its native desktop lineup. The ChatGPT desktop app for Linux is now available in preview, bringing integrated workflows, local file access, and Codex tooling directly to native Linux environments. Here is a complete rundown of what’s included, supported distributions, installation steps, and current limitations. Supported Distributions & Architectures The preview release targets mainstream Debian- and Red Hat–based desktop environments across both x64 (x86_64) and ARM64 (aarch64) hardware architectures: Ubuntu: 24.04 LTS and 26.04 LTS Debian: Debian 13 Fedora: Fedora 43 and 44 To verify your system architecture before downloading, run: uname -m x86_64 indicates an x64 processor. aarch64 or arm64 indicates an ARM64 processor. Installation Guide OpenAI provides native .deb and .rpm packages, which automatically configure ...

ChatRTX: Your Personalized Assistant by NVIDIA


Ever wished for a powerful AI chatbot like ChatGPT or Gemini, running on your PC and using your own files, without cloud uploads? NVIDIA's ChatRTX  makes this possible, bringing generative AI to your desktop.


Unlike cloud-based chatbots, ChatRTX runs entirely on your Windows PC. Your data remains private. This is ideal for privacy-conscious users or those handling sensitive information.  No internet connection is needed after setup!

ChatRTX uses Retrieval-Augmented Generation (RAG). You can point it to a folder of documents (.txt, .pdf, .doc/.docx, .xml) or YouTube URLs.  It uses this information to answer your questions. Imagine querying your project notes or research papers for summarized answers—a real productivity boost!

Using your NVIDIA RTX graphics card, ChatRTX often provides answers faster than cloud services, especially for local files.

NVIDIA also offers ChatRTX as a reference project. This benefits developers learning to build applications using technologies like TensorRT-LLM for optimizing AI models on RTX hardware.


You need a Windows 11 PC with an NVIDIA GeForce RTX 30-series, 40-series, or 50-series GPU (or equivalent professional cards) and at least 8GB of VRAM. This excludes many users without high-end systems. Updated drivers are also required.

Running locally, ChatRTX lacks access to constantly updated internet information. Its knowledge is limited to the base AI model (like Mistral or Llama) and your provided files. Don't expect current news unless you supply relevant documents.

ChatRTX's AI models, while powerful, are smaller than those powering cloud services. This may lead to less nuanced responses or inaccuracies.

As a tech demo, it may lack the polish or features of a commercial product. Setup might require technical expertise.

Running AI models locally uses significant GPU resources.  Heavy AI use alongside gaming or other demanding tasks may impact performance.


ChatRTX offers a promising glimpse of personalized, private AI. Securely querying local data is fantastic for productivity and specialized tasks. It's a step towards democratizing powerful AI.

However, the high hardware requirements are a barrier. It's clearly aimed at users with NVIDIA RTX hardware.

For tech enthusiasts, developers, and those with compatible hardware prioritizing privacy and local data, ChatRTX is worth exploring. It could become your personal digital assistant. For others, it showcases future possibilities, but cloud-based chatbots remain more accessible.

Comments