

Ollama’s 0.40.15 release notes list additions for local model users and developers. Among them are support for Xiaomi MiMo v2.6 9B and an integration for launching the Kimi Code CLI.
The notes also describe changes affecting parallel requests and context handling for Qwen models. Model compatibility does not establish that a particular checkpoint will fit every machine or perform well at a given context length; check the model’s own requirements and license alongside the runtime release.
Before updating a working setup
Review the release notes and back up important configuration before changing an inference server used by other applications. An update to a shared service can affect more than one workflow, so test against representative requests when it is practical.
We have not installed this release or measured its performance. Ollama’s local runtime and any optional hosted services are separate choices, with their own requirements and terms.
EXPLORE THE SOURCE
Projects in this story
GitHub repositories
- ollama/ollama ↗View project details
Independent reporting based on the linked sources. Product and performance claims are attributed to their publishers unless noted.



