v0.14.3
📦 ollamaView on GitHub →
✨ 5 features🐛 5 fixes🔧 5 symbols
Summary
This release introduces several new powerful image generation and LLM models, including Z-Image Turbo and GLM-4.7-Flash. It also includes several bug fixes related to macOS shutdown, model management, and API usage.
✨ New Features
- Added Z-Image Turbo (6B parameter text-to-image model from Alibaba342200231s Tongyi Lab).
- Added Flux.2 Klein (Black Forest Labs342200231s fastest image-generation models).
- Added GLM-4.7-Flash (strongest model in the 30B class for lightweight deployment).
- Added LFM2.5-1.2B-Thinking (new hybrid model family for on-device deployment).
- The /api/generate API can now be used for image generation.
🐛 Bug Fixes
- Fixed issue where Ollama's macOS app would interrupt system shutdown.
- Fixed 'ollama create' and 'ollama show' commands for experimental models.
- Fixed minor issues in Nemotron-3-Nano tool parsing.
- Fixed issue where removing an image generation model would cause it to first load.
- Fixed issue where 'ollama rm' would only stop the first model in the list if it were running.