{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreieracuvwckla64jizt5um5v7slalx26vnm3ubvjgrt27sscbw6hoe",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mforuxhe4nr2"
  },
  "path": "/t/m-courtyard-native-mac-app-for-local-fine-tuning-export-to-lm-studio-ollama/173761#post_1",
  "publishedAt": "2026-02-25T11:35:19.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "https://github.com/Mcourtyard/m-courtyard",
    "Releases Page"
  ],
  "textContent": "Hi everyone,\n\nI’ve been working on **M-Courtyard** , an open-source, fully local fine-tuning app built specifically for Apple Silicon (using **`mlx_lm`**).\n\nI built this because I found the workflow on Mac a bit fragmented. Training is one thing, but actually _using_ the model afterwards was often a pain.\n\nWith the new v0.4.7 update, I’ve focused on closing that loop. You can now:\n\n  * **Export to MLX** : Directly outputs fused safetensors that you can drag-and-drop into **LM Studio**.\n\n  * **Local Inference Server** : One-click start a local OpenAI-compatible API server. Connects instantly to **OpenWebUI** , **Chatbox** , or your own code.\n\n  * **Ollama** : Still supports 1-click export to Ollama, but now keeps the fused model files too.\n\n\n\n\nIt handles the setup for you (Python env, dependencies) so you don’t need to fight with terminal configs.\n\n**Repo:** **https://github.com/Mcourtyard/m-courtyard** **Download (DMG):** **Releases Page**\n\nWould love any feedback from Mac users here!\n\n\n\n\n\n\n\n",
  "title": "M-Courtyard - Native Mac app for local fine-tuning (export to LM Studio/Ollama)"
}