GPT4All

This release introduces dedicated configuration tabs for remote models like Groq, OpenAI, and Mistral, and improves compatibility by supporting older CUDA devices. It also includes fixes for crashes and better handling of whitespace for DeepSeek-R1 models.

This release introduces support for OLMoE and Granite MoE models, alongside several critical bug fixes addressing issues in LocalDocs, DeepSeek reasoning output, and stability on Windows ARM devices.

This release introduces robust native support for the DeepSeek-R1 model family and completely overhauls the chat template parser for improved model compatibility. Several critical bugs related to the code interpreter and local server functionality have also been resolved.

This release introduces official support for Windows ARM devices and includes significant stability fixes for macOS update/quit operations, alongside improvements to the Code Interpreter and chat template parsing.