PR #15443: mlx: remove stale x86 libmlx library

• Repository: ollama/ollama
• Author: dhiltgen
• State: closed | merged: True
• Link: https://github.com/ollama/ollama/pull/15443

Description (problem / solution / changelog)

Fixes #15433

The release contains an extraneous library from the old pattern of placing it at the top.

% find app -name \*mlx\*.dylib | xargs file
app/Ollama.app/Contents/Resources/libmlx.dylib:               Mach-O 64-bit dynamically linked shared library x86_64
app/Ollama.app/Contents/Resources/mlx_metal_v3/libmlx.dylib:  Mach-O universal binary with 2 architectures: [x86_64:Mach-O 64-bit dynamically linked shared library x86_64] [arm64]
app/Ollama.app/Contents/Resources/mlx_metal_v3/libmlx.dylib (for architecture x86_64):	Mach-O 64-bit dynamically linked shared library x86_64
app/Ollama.app/Contents/Resources/mlx_metal_v3/libmlx.dylib (for architecture arm64):	Mach-O 64-bit dynamically linked shared library arm64
app/Ollama.app/Contents/Resources/mlx_metal_v3/libmlxc.dylib: Mach-O universal binary with 2 architectures: [x86_64:Mach-O 64-bit dynamically linked shared library x86_64] [arm64:Mach-O 64-bit dynamically linked shared library arm64]
app/Ollama.app/Contents/Resources/mlx_metal_v3/libmlxc.dylib (for architecture x86_64):	Mach-O 64-bit dynamically linked shared library x86_64
app/Ollama.app/Contents/Resources/mlx_metal_v3/libmlxc.dylib (for architecture arm64):	Mach-O 64-bit dynamically linked shared library arm64
app/Ollama.app/Contents/Resources/libmlxc.dylib:              Mach-O 64-bit dynamically linked shared library x86_64
app/Ollama.app/Contents/Resources/mlx_metal_v4/libmlx.dylib:  Mach-O 64-bit dynamically linked shared library arm64
app/Ollama.app/Contents/Resources/mlx_metal_v4/libmlxc.dylib: Mach-O 64-bit dynamically linked shared library arm64

The mlx_metal_v3 version is correctly lipo'd to support both architectures, so this top-level x86-only version was not supposed to be retained.

With this fix:

% find dist/Ollama.app -name \*mlx\*.dylib | xargs fi
le
dist/Ollama.app/Contents/Resources/mlx_metal_v3/libmlx.dylib:  Mach-O universal binary with 2 architectures: [x86_64:Mach-O 64-bit dynamically linked shared library x86_64] [arm64]
dist/Ollama.app/Contents/Resources/mlx_metal_v3/libmlx.dylib (for architecture x86_64):	Mach-O 64-bit dynamically linked shared library x86_64
dist/Ollama.app/Contents/Resources/mlx_metal_v3/libmlx.dylib (for architecture arm64):	Mach-O 64-bit dynamically linked shared library arm64
dist/Ollama.app/Contents/Resources/mlx_metal_v3/libmlxc.dylib: Mach-O universal binary with 2 architectures: [x86_64:Mach-O 64-bit dynamically linked shared library x86_64] [arm64:Mach-O 64-bit dynamically linked shared library arm64]
dist/Ollama.app/Contents/Resources/mlx_metal_v3/libmlxc.dylib (for architecture x86_64):	Mach-O 64-bit dynamically linked shared library x86_64
dist/Ollama.app/Contents/Resources/mlx_metal_v3/libmlxc.dylib (for architecture arm64):	Mach-O 64-bit dynamically linked shared library arm64
dist/Ollama.app/Contents/Resources/mlx_metal_v4/libmlx.dylib:  Mach-O 64-bit dynamically linked shared library arm64
dist/Ollama.app/Contents/Resources/mlx_metal_v4/libmlxc.dylib: Mach-O 64-bit dynamically linked shared library arm64

Changed files

• scripts/build_darwin.sh (modified, +6/-1)

PR #30: Add image generation model and update provider to support it

• Repository: Fueled/ai-provider-for-ollama
• Author: milindmore22
• State: open | merged: False
• Link: https://github.com/Fueled/ai-provider-for-ollama/pull/30

Description (problem / solution / changelog)

Description of the Change

This PR adds support for Image generation model based on experimental feature of ollama please refer blog

This pull request adds support for image generation models to the Ollama provider integration. The most significant changes include the introduction of a new OllamaImageGenerationModel class, updates to model metadata detection to identify image generation capabilities, and enhancements to provider logic to instantiate the correct model type based on capabilities.

Image Generation Model Support:

• Added a new OllamaImageGenerationModel class that implements image generation using the Ollama /api/generate endpoint, including prompt extraction, response parsing, and custom timeout handling.
• Updated the provider logic in OllamaProvider to instantiate OllamaImageGenerationModel when a model supports image generation, based on its capabilities. [1] [2]

Model Metadata Detection:

• Enhanced OllamaModelMetadataDirectory to detect image generation models by checking for the 'image' capability, and to construct appropriate ModelMetadata for such models with relevant options and output types. [1] [2] [3] [4]

Tooling and Static Analysis:

• Updated phpstan.neon.dist to temporarily ignore the new OllamaImageGenerationModel.php file for static analysis, consistent with other files depending on unreleased WordPress core AI Client classes.

[!WARNING] Supported only on MacOS (because experiments are only avilable on MacOS) Tested with x/flux2-klein and x/z-image-turbo

Screenshots

1. Verify the model is ready by visiting Settings->Ollama Settings

   <img width="1470" height="836" alt="Screenshot 2026-03-24 at 4 16 23 PM" src="https://github.com/user-attachments/assets/5a680349-01e8-4ab9-ba35-cc9dfe19a955" />

2. Visit Media->Generate Image, Enter prompt

   <img width="1470" height="836" alt="Screenshot 2026-03-24 at 4 17 19 PM" src="https://github.com/user-attachments/assets/2d742da5-5849-4e90-a06f-15f7a06b85d0" />

3. Generate Image

   <img width="1470" height="836" alt="Screenshot 2026-03-24 at 4 21 28 PM" src="https://github.com/user-attachments/assets/83afb232-db71-4b08-9c41-4ecaa297d99e" />

4. Image in Media Gallery After saving it.

   <img width="1470" height="836" alt="Screenshot 2026-03-24 at 4 25 41 PM" src="https://github.com/user-attachments/assets/42f580f9-01ea-4a4a-8219-193239b47cee" />

Closes #

How to test the Change

Download Model

ollama pull x/flux2-klein

Test Model

ollama run x/flux2-klein "a cat holding a sign that says hello world"

Test Curl

curl http://localhost:11434/api/generate -d '{
  "model": "x/flux2-klein",
  "prompt": "a cat holding a sign that says hello world",
  "stream": false
}'

Now you can try generate Image in WordPress

Changelog Entry

Added - support Image generation model

Credits

Props @milindmore22

Checklist:

• I agree to follow this project's Code of Conduct.
• I have updated the documentation accordingly.
• I have added Critical Flows, Test Cases, and/or End-to-End Tests to cover my change.
• All new and existing tests pass.

Changed files

• includes/Metadata/OllamaModelMetadataDirectory.php (modified, +44/-3)
• includes/Models/OllamaImageGenerationModel.php (added, +217/-0)
• includes/Provider/OllamaProvider.php (modified, +8/-0)
• phpstan.neon.dist (modified, +1/-0)
• tests/Integration/Metadata/OllamaModelMetadataDirectoryTest.php (modified, +103/-0)
• tests/Integration/Models/OllamaImageGenerationModelTest.php (added, +332/-0)
• tests/Integration/Provider/OllamaProviderTest.php (modified, +85/-1)