Ollama released v0.40.9 on October 22, 2026. The release adds speech generation, a new decision-model family and cross-platform support for the Flint coding model. Read the release notes.
Speech with Phonon
Ollama can now generate speech with Phonon on Apple Silicon. ollama run plays text or a chat model's reply aloud as the audio is generated, and applications can stream audio through the OpenAI-compatible /v1/audio/speech endpoint:
ollama run phonon "Hello from Ollama."d3 decision models
d3 brings vLLM Semantic Router's decision models to Ollama. Given text, structured state or an image, the models classify, answer yes-or-no questions, or score options with probabilities. The family ships in 2B, 4B, 9B and 27B sizes:
ollama run d3 "A customer says their card was charged twice." --ask "Is this a billing issue?"Flint beyond macOS
Flint, the Recursive coding model added in v0.40.8, now runs on Linux and Windows as well as macOS.
Other improvements
- Streaming OpenAI Responses and Anthropic Messages requests now report generation failures instead of ending silently after partial output.
ollama launchpasses cloud models' context lengths and capabilities to coding tools, fixing incorrect context and compaction settings.- Anthropic-compatible web search now uses the model's supported thinking setting in follow-up requests, preventing avoidable failures.
This report covers the October 22 release notes; the previous release is covered in our v0.40.8 Flint report.