Ollama has released version 0.30.9, incorporating several updates and fixes. Key changes include support for the Cohere2Moe architecture and improvements to the LFM2 parser. The release also addresses an issue where coding agent use cases would only output a single token and implements a new error check for messages exceeding the context window. Additionally, the release updates llama.cpp to a specific commit, b9637, enhancing its integration. AI
IMPACT Ollama's latest release improves local AI model execution with new architecture support and bug fixes.
RANK_REASON This is a software release for a tool that runs AI models locally, not a new frontier model release or research paper.
AI-generated summary · Google Gemini · from 4 sources. How we write summaries →
