# M-Courtyard - Native Mac app for local fine-tuning (export to LM Studio/Ollama)

**URL:** <https://discuss.huggingface.co/t/m-courtyard-native-mac-app-for-local-fine-tuning-export-to-lm-studio-ollama/173761>\
**Category:** Show and Tell\
**Created:** [February 25, 2026, 11:35am UTC](https://discuss.huggingface.co/t/m-courtyard-native-mac-app-for-local-fine-tuning-export-to-lm-studio-ollama/173761 "2026-02-25T11:35:18Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![tuwenbo](https://avatars.discourse-cdn.com/v4/letter/t/e99b99/32.png) [@tuwenbo](https://discuss.huggingface.co/u/tuwenbo)\
**Post date:** [February 25, 2026, 11:35am UTC](https://discuss.huggingface.co/t/m-courtyard-native-mac-app-for-local-fine-tuning-export-to-lm-studio-ollama/173761/1 "2026-02-25T11:35:19Z")

</div>

Hi everyone,

I’ve been working on **M-Courtyard** , an open-source, fully local fine-tuning app built specifically for Apple Silicon (using **`mlx_lm`** ).

I 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.

With the new v0.4.7 update, I’ve focused on closing that loop. You can now:

- **Export to MLX** : Directly outputs fused safetensors that you can drag-and-drop into **LM Studio**.

- **Local Inference Server** : One-click start a local OpenAI-compatible API server. Connects instantly to **OpenWebUI** , **Chatbox** , or your own code.

- **Ollama** : Still supports 1-click export to Ollama, but now keeps the fused model files too.

It handles the setup for you (Python env, dependencies) so you don’t need to fight with terminal configs.

**Repo:** **[https://github.com/Mcourtyard/m-courtyard](https://github.com/Mcourtyard/m-courtyard)** **Download (DMG):** **[Releases Page](https://github.com/Mcourtyard/m-courtyard/releases)**

Would love any feedback from Mac users here!

 ![iShot_2026-02-25_18.21.39](https://us1.discourse-cdn.com/hellohellohello/original/3X/3/e/3e9f770f038eaabac3f64ea0fd545026649d009b.png)

 ![iShot_2026-02-25_18.19.49](https://us1.discourse-cdn.com/hellohellohello/original/3X/0/2/0273171315ff83abc55df8e2f9d1628ee22bd710.png)

 ![03 Train Model_03](https://us1.discourse-cdn.com/hellohellohello/original/3X/3/2/320701d53dec0bbb25663b498467ecc700cf2603.png)

 ![02 Data Preparation_03](https://us1.discourse-cdn.com/hellohellohello/original/3X/3/6/3682339f7a939fcdc74515e0df2c35606d3da00b.png)

---

<div class="post-metadata">

**Author:** ![JT-UncSoft](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jt-uncsoft/32/57859_2.png) [@JT-UncSoft](https://discuss.huggingface.co/u/JT-UncSoft)\
**Post date:** [February 26, 2026, 4:35am UTC](https://discuss.huggingface.co/t/m-courtyard-native-mac-app-for-local-fine-tuning-export-to-lm-studio-ollama/173761/2 "2026-02-26T04:35:12Z")

</div>

This looks really cool - I will check it out!

---

<div class="post-metadata">

**Author:** ![tuwenbo](https://avatars.discourse-cdn.com/v4/letter/t/e99b99/32.png) [@tuwenbo](https://discuss.huggingface.co/u/tuwenbo)\
**Post date:** [February 27, 2026, 6:38am UTC](https://discuss.huggingface.co/t/m-courtyard-native-mac-app-for-local-fine-tuning-export-to-lm-studio-ollama/173761/3 "2026-02-27T06:38:38Z")

</div>

We welcome your valuable suggestions.👏