🚀 New Features
New models on llama.cpp TurboQuant — DeepSeek V4 Flash and Kimi K3
- DeepSeek V4 Flash 0731 runs
- Kimi K3 fully supported, vision included
- AMD on Linux x64 now covers RDNA2–RDNA4 and CDNA
- Synced with the latest upstream llama.cpp
🔧 Improvements & Fixes
- Downloads no longer fail when the pre-check does
- Clearer model-load errors, and recoverable ones now retry
- Windows: models in folders with non-Latin names now load
- MLX models with legacy or misnamed shards now load
- Favorites no longer list the same model twice
- Proper icon for the Codex integration
- Smaller UI and stability cleanups
🙏 Contributors
Thanks to @Vect0rM, @worthant, @yl-atomic for their contributions to this release!