Local speech output now works through an OpenAI-compatible /v1/audio/speech endpoint on Apple Silicon. streamingSending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.Full definition → Responses and Messages requests now report failures instead of silently truncating.
Key takeaways · AI-distilled
Ollama v0.40.9 adds d3, vLLM Semantic Router's decision models in 2B, 4B, 9B and 27B sizes, which take text, structured state or an image and classify, answer yes or no, or score options with probabilities.
Speech in Ollama runs on the Phonon model on Apple Silicon: `ollama run` plays text or a chat model's reply aloud while the audio is still being generated.
`ollama launch` now passes cloud models' context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → lengths and capabilities to coding tools, fixing cases where those tools ran with incorrect context and context compactionSummarizing an agent's earlier conversation to free room in the context window so a long session can keep going.Full definition → settings.
Ollama's Anthropic-compatible web search now uses the model's supported thinking setting in follow-up requests, and the Flint model now runs on Linux and Windows as well as macOS.
Terms in this piece · Glossary
streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
