ai-file-sorter

G5KB.png) - Review, edit and confirm or continue later You can download the installer for Windows in [Releases](https://github.com/hyperfield/ai-file-sorter/releases) or the Standalone ZIP from the [app's website](https://filesorter.app/download/). Installers for Linux and macOS are coming up. You can, however, easily [build the app from source](https://github.com/hyperfield/ai-file-sorter/blob/main/READM...) for Linux or macOS. --- ### How it works 1. You choose which model you want the app to interface with. The app will download the model for you. You can switch models later on. 2. You point the app at a folder, and it feeds a prompt to the model. 3. It then suggests folder categories like `Operating Systems / Linux distributions`, `Programming / Scripts`, `Images / Logos`, etc. You can review and approve before anything is moved, and you can continue the same sorting session later from where you left off. Models tested: - LLaMa 3 (3B) - Mistral (7B) - With CUDA / OpenCL / OpenBLAS support - Other GPU back-ends can also be enabled on `llama.cpp` compile --- ### Try it out * Windows: [SourceForge](https://sourceforge.net/projects/ai-file-sorter/) or [GitHub Releases](https://github.com/hyperfield/ai-file-sorter/releases) * Linux/macOS: build from source (instructions in the [README](https://github.com/hyperfield/ai-file-sorter/blob/main/READM...)) --- I’d love feedback from others using local models, especially around: - Speed and accuracy in categorizing files - Model suggestions that might be more efficient than Mistral/LLaMa - Any totally different way to approach this problem? - Is this local LLM use case actually useful to you or people like you, or should the app shift its focus? Thanks for reading!