Ollama 0.40.4 is out: highlights and upgrade guide
At a glance
Ollama 0.40.4 is a patch release published on Oct 12, 2026. It follows Ollama 0.40.3 by 1 day. It includes 11 listed changes.
- Kev decision models are now supported by the MLX runner on Apple silicon
- ollama launch can now be used with usage credits without upgrading to a paid plan
- ollama launch codex now includes locally installed Ollama models in its model picker. Use /model within the Codex CLI to swap models.
- Improved inference performance by reusing verified manifests and already loaded models
- Added support for multimodal embeddings through llama-server
- Version
- 0.40.4
- Released
- Oct 12, 2026
- Release type
- Patch
- Previous
- 0.40.3
- Changes listed
- 11
- License
- MIT
How to upgrade to Ollama 0.40.4
This is a patch release, normally bug fixes only. It is usually safe to upgrade after your tests pass.
curl -fsSL https://ollama.com/install.sh | shDownload the installer from ollama.com/download
What's included in Ollama 0.40.4
Details from the official release page.
Decision models in the CLI
Decision models can now be used directly from the terminal with ollama run — ask yes/no questions, classify text into labels, or score against a rubric:
ollama run nimble --ask "Is a refund being requested?" < ticket.txt
## What's Changed
* Kev decision models are now supported by the MLX runner on Apple silicon
* ollama launch can now be used with usage credits without upgrading to a paid plan
* ollama launch codex now includes locally installed Ollama models in its model picker. Use /model within the Codex CLI to swap models.
* Improved inference performance by reusing verified manifests and already loaded models
* Added support for multimodal embeddings through llama-server
* Fixed loading multimodal embedding models with small context windows
* Improved Gemma 4 prefill performance on NVIDIA GPUs with the MLX runner
* MLX runner now clips long Laya states instead of rejecting them
* Improved speculative decoding reliability in the MLX runner, including recurrent state handling after rollback
* Updated llama.cpp with native decision model support
* Updated README and documentation with clearer privacy and cloud-services wording
Ollama 0.40.4 FAQ
When was Ollama 0.40.4 released?
Ollama 0.40.4 was published on Oct 12, 2026.
Is Ollama 0.40.4 a major update?
No. It is a patch release, mainly bug fixes.
How do I upgrade to Ollama 0.40.4?
Use the commands in the “How to upgrade” section, then run your test suite.
Where are the official Ollama 0.40.4 notes?
On the project's official release page: https://github.com/ollama/ollama/releases/tag/v0.40.4
Source: official Ollama v0.40.4 release. Spotted an error? Tell us.