Ollama 0.3.13 is here

Ollama 0.3.13 is here

by

Ollama 0.3.13 is here! There are new safety models available! (Meta’s Llama Guard 3 and Google’s ShieldGemma). For contributors, devs have been working on a new Go runner for improved reliability and caching. Please give it a try!

New safety models

  • Llama Guard 3: a series of models by Meta, fine-tuned for content safety classification of LLM inputs and responses.
  • ShieldGemma: ShieldGemma is set of instruction tuned models from Google DeepMind for evaluating the safety of text prompt input and text output responses against a set of defined safety policies.

What’s Changed

  • Default model in quickstart is now llama3.2
  • Fixed issue where ollama pull would leave connections when encountering an error
  • ollama rm will now stop a model if it is running prior to deleting it

New Go runner (for contributors):

Ollama is transitioning to a new Go-based subprocess model runner with improved reliability and caching. This new runner found under the llama directory replaces the previous code under llm/ext_server. During this transition period, the new Go runner is opt-in at build time, and requires using a different approach to build. For more information see development.md.

New Contributors

Full Changelog: v0.3.12…v0.3.13