UI: https://ui.shadcn.com/ with https://v0.dev/ for rapid development. - Source: Hacker News / about 1 month ago

We're even opinionated to the point of having our own "CSS rule engine" that the AI should follow, to make sure that the padding is always the same when adding new elements on to the screen, so the goal is for you to not write code as far as possible. Have a look at https://v0.dev, it paints a good picture of what we're trying to do with this. - Source: Hacker News / 2 months ago

For development of the UI components, we tried something new. Vercel has this new AI tool called v0.dev that allows developers to take advantage of shadcn/ui and Tailwind using nothing but words, which can then be easily downloaded to your local project using nothing but a simple npx command. - Source: dev.to / 2 months ago

v0 by Vercel could be worth a look: https://v0.dev From the FAQ: "v0 is a generative user interface system by Vercel powered by AI. It generates copy-and-paste friendly React code based on shadcn/ui and Tailwind CSS that people can use in their projects". - Source: Hacker News / 3 months ago

v0.dev — v0 uses AI models to generate code based on simple text prompts. It generates copy-and-paste friendly React code based on shadcn/ui and Tailwind CSS that people can use in their projects. Each generation takes at minimum 30 credits. You start up with 1200 credits, and get 200 free credits every month. - Source: dev.to / 4 months ago

I focused on supporting Ollama, GPT4All, and LMStudio, all of which run smoothly on a Mac computer. Many of these tools are user-friendly wrappers around Llama.cpp, allowing easy model downloads and providing a REST interface to query the available models. Last week, I also added "👋🏼 Jan" support because HuggingFace has endorsed this provider out-of-the-box. - Source: dev.to / 5 days ago

Ollama is an open-source tool for using LLMs like Llama 3 on your computer. Thanks to new research, these models don't need a lot of VRAM, computing power, or storage. They are designed to work well on laptops. - Source: dev.to / 16 days ago

One thing I've noticed is that gemma is much less verbose by default. [0] https://github.com/ollama/ollama. - Source: Hacker News / about 2 months ago

A few weeks ago, I started using Ollama to run language models (LLM), and I've been really enjoying it a lot. After getting the hang of it, I thought it was about time to try it out on one of our real-world cases (I'll share more about this later). - Source: dev.to / 2 months ago

GitHub - ollama/ollama: Get up and running with Llama 2, Mistral, Gemma, and other large language models. - Source: dev.to / 3 months ago