Skip to content
View Amix29's full-sized avatar
💻
I'm currently working on Soup! It's exciting....
💻
I'm currently working on Soup! It's exciting....

Block or report Amix29

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Amix29/README.md

Hi, I'm Amix 👋

I'm 14 years old and I'm passionate about artificial intelligence 🤖.


Description GitHub

I joined GitHub in 2023, but I've been really active since early 2026. I started using AI back when ChatGPT was released in January 2022.

At first, I was just experimenting a bit by posting videos on TikTok 📱. Then I saw a YouTube video 🎥 that showed ChatGPT could code a working calculator. I thought it was incredible that AI could code things.

Then the years went by, and I kept experimenting with different AIs and tools: ChatGPT, Claude, Bolt, Lovable, etc. 🧪

Then DeepSeek and Qwen came along. The more Chinese models were released, the more I became interested in open source 🌐, and I think it’s incredible that the Chinese manage to innovate with every new release.

On May 31, 2026, I released Multi-Converter, my very first project 🚀. That’s when the entire open-source AI ecosystem really started to interest me.

I don’t know how to code, but I think that today, it’s still very important to have the basics and a certain developer’s mindset 💻.

In my opinion, the future of AI isn’t about subscriptions or the cloud—it’s about on-premises AI 🖥️, which almost anyone will be able to run simply by using open-source projects and connecting them to open-source apps.

I also think that AI models shouldn’t be proprietary, but open source 🔓, to prevent a single entity from controlling a field as important as AI.


🔬 Interests

🖥️ Local AI 🌐 Open Source AI
🧠 Large Language Models 🧪 Fine-tuning & Model Distillation
⚡ Inference & Performance Optimization 📦 Quantization

🤝 Contributions

🥣 Soup

I contribute to Soup, an open-source toolkit designed to make LLM fine-tuning more accessible.

My contributions mainly focus on:

  • 🐛 Finding and investigating bugs
  • 🧪 Testing features and training methods
  • ⚡ Performance and memory optimizations
  • 🧠 Fine-tuning and model distillation
  • 🍎 MLX and local AI
  • 💡 Researching and proposing new features
  • 🧪 Model Distillation

🚀 Projects

My first public project, released on May 31, 2026.

A local application designed to convert files directly on your machine.

📊 GitHub Activity

🔥 12

Longest Streak

✅ 62

Pull Requests merged


💡 What I Want to Build

Tools that make local and open-source AI easier, faster and more accessible.


📫 Contact

🐙 GitHub: @Amix29

📧 Email: amixdigital0@gmail.com

▶️ YouTube: My YouTube Channel

Pinned Loading

  1. Multi-Converter Multi-Converter Public

    Multi-Converter is an easy-to-use conversion program with a wide range of supported formats. It’s simple, fast, and powerful.

    JavaScript 5

  2. MakazhanAlpamys/Soup MakazhanAlpamys/Soup Public

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Python 7.4k 1.2k