{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiae7w3qbp6yf3al57s6d66oxkshlxxlmpjepeqrg5cviothmjyady",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3meqzasdw4vc2"
  },
  "path": "/t/m-courtyard-fine-tune-llms-on-macos-with-zero-code-mlx-ollama-gui/173463#post_1",
  "publishedAt": "2026-02-13T16:05:53.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "GitHub - tuwenbo0120/m-courtyard: M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.",
    "Release M-Courtyard v0.3.0 · tuwenbo0120/m-courtyard · GitHub"
  ],
  "textContent": "Hi everyone!\n\nI’d like to share M-Courtyard, an open-source macOS desktop app for fine-tuning\nLLMs on Apple Silicon — no code, no cloud, everything local.\n\nIt wraps the full pipeline in a native GUI:\nImport docs →  Generate training data (Ollama) →  LoRA fine-tune (mlx-lm)\n→  Chat-test →  One-click export to Ollama (Q4/Q8/F16)\n\nSupports models from mlx-community: Qwen 3, DeepSeek R1, GLM, Llama 3, and more.\n\n  * GitHub: GitHub - tuwenbo0120/m-courtyard: M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.\n  * Download: Release M-Courtyard v0.3.0 · tuwenbo0120/m-courtyard · GitHub\n  * License: AGPL 3.0\n  * Tech: Tauri 2.x (Rust) + React + mlx-lm\n\n\n\nRequirements: macOS 14+, Apple Silicon (M1/M2/M3/M4), 16GB+ RAM recommended\n\nFeedback and suggestions welcome!\n\n\n\n\n\n",
  "title": "M-Courtyard: Fine-tune LLMs on macOS with zero code (MLX + Ollama GUI)"
}