Large artificial intelligence models on personal computers
FlashML-org/FreeToken is a library that enables running data center-scale large artificial intelligence models quickly and efficiently on personal computers. It allows users to run Mixture of Experts (MoE) models with over 290 billion parameters at interactive speeds on standard hardware.
Updates
- November 6, 2026: Stars 15,664 → 16,721, latest release v0.2.1 (October 26, 2026).
- November 2, 2026: Stars 15,543 → 15,664, latest release v0.2.1 (October 26, 2026).
What you get
- Combines used hardware resources into a single artificial intelligence infrastructure.
- Provides dynamic resource management between GPU memory VRAM and main memory.
- Runs large Mixture of Experts architecture MoE models on local devices at interactive speeds.
Installation
uv pip install "freetoken[accel]"git clone https://github.com/FlashML-org/FreeToken.git && cd FreeToken
uv venv && source .venv/bin/activate
uv pip install -e ".[accel]"If you don't write code
You need to install the FreeToken library, which allows running large AI models on a local computer. To install it using the fast package manager uv, you can use the command uv pip install "freetoken[accel]". If you want to compile it directly from the source code, you can run the command sequence git clone https://github.com/FlashML-org/FreeToken.git && cd FreeToken uv venv && source .venv/bin/activate uv pip install -e ".[accel]"
Repository: https://github.com/FlashML-org/FreeToken. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-11-02: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.