Impact Score: 5/10
Ollama v0.40.4 — Release Notes & Engineering Impact
Source available — automated, not human-reviewed
Component: ollama · Channel: stable. Automated analysis, not a compatibility certification. How this works.
Analysis updated: 2026-11-01.
⚡ Executive Summary (TL;DR)
Ollama v0.40.4. Source highlight: Decision models in the CLI
Who Does This Impact? (Role-Based Analysis)
💻 Software Engineers & Devs
Check the source notes against the package and APIs you use before upgrading.
📊 Product & Engineering Leads
Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.
⚙️ DevOps & Security
Verify the target version, runtime requirements and rollback procedure in the official documentation.
✨ New Features & Capabilities (1)
- Added support for multimodal embeddings through llama-server
⚡ Performance & Enhancements (3)
- Improved inference performance by reusing verified manifests and already loaded models
- Improved Gemma 4 prefill performance on NVIDIA GPUs with the MLX runner
- Improved speculative decoding reliability in the MLX runner, including recurrent state handling after rollback
🔧 Bug Fixes & Patches (1)
- Fixed loading multimodal embedding models with small context windows
📄 View Raw Release Notes (Original Developer Log)
## 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
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.3...v0.40.4