mlx-swift-examples

# MLX Swift Examples

Example [MLX Swift](https://github.com/ml-explore/mlx-swift) programs.  The language model
examples use models implemented in [MLX Swift LM](https://github.com/ml-explore/mlx-swift-lm).

- [MNISTTrainer](Applications/MNISTTrainer/README.md): An example that runs on
  both iOS and macOS that downloads MNIST training data and trains a
  [LeNet](https://en.wikipedia.org/wiki/LeNet).

- [LLMBasic](Applications/LLMBasic/README.md): A **minimal** LLM chat example
  application.  It has only two features: load the model and evaluate a prompt.

- [LLMEval](Applications/LLMEval/README.md): An example that runs on both iOS
  and macOS that downloads an LLM and tokenizer from Hugging Face and
  generates text from a given prompt.  It has some preset prompts, tool integration,
  etc.  Additionally it shows detailed statistics on the run.

- [MLXChatExample](Applications/MLXChatExample/README.md): An example chat app that runs on both iOS and macOS that supports LLMs and VLMs.

- [LoRATrainingExample](Applications/LoRATrainingExample/README.md): An example that runs on macOS that downloads an LLM and fine-tunes it using LoRA (Low-Rank Adaptation) with training data.

- [LinearModelTraining](Tools/LinearModelTraining/README.md): An example that
  trains a simple linear model.

- [StableDiffusionExample](Applications/StableDiffusionExample/README.md): An
  example that runs on both iOS and macOS that downloads a stable diffusion model
  from Hugging Face and  and generates an image from a given prompt.

- [llm-tool](Tools/llm-tool/README.md): A command line tool for generating text
  using a variety of LLMs available on the Hugging Face hub.

- [image-tool](Tools/image-tool/README.md): A command line tool for generating images
  using a stable diffusion model from Hugging Face.

- [mnist-tool](Tools/mnist-tool/README.md): A command line tool for training a
  a LeNet on MNIST.

## Numerical Computing

Examples that use MLX for general numerical computing (no ML model involved),
useful for seeing how MLX array idioms, `compile`, and custom Metal kernels
apply to classic numerical problems.

- [CurveFit](Numerical/CurveFit/README.md): Live visualization of gradient
  descent fitting a quadratic to noisy samples, using `MLX.grad` for
  automatic differentiation.

- [HeatTransfer](Numerical/HeatTransfer/README.md): 2D heat-diffusion
  simulation comparing three Jacobi/SOR stencil implementations
  (`conv2d`, compiled `roll`, red/black SOR).

- [Mandelbrot](Numerical/Mandelbrot/README.md): Mandelbrot set renderer
  comparing plain MLX, compiled MLX, and a custom Metal kernel
  (`MLXFast.metalKernel`) against a reference CPU implementation.

> [!IMPORTANT]
> `MLXLMCommon`, `MLXLLM`, `MLXVLM` and `MLXEmbedders` have moved to a new repository
> containing _only_ reusable libraries: [mlx-swift-lm](https://github.com/ml-explore/mlx-swift-lm).

Previous URLs and tags will continue to work, but going forward all updates to these
libraries will be done