語音
Ollama 現在可以在 Apple Silicon 上使用 Phonon 生成語音。ollama run 會在生成音訊時朗讀文字或聊天模型的回覆，應用程式可以通過相容 OpenAI 的 /v1/audio/speech 端點流式傳輸音訊。
ollama run phonon " Hello from Ollama. "
d3 決策模型
d3 將 vLLM Semantic Router 的決策模型引入 Ollama。給模型提供文字、結構化狀態或影像，並要求它進行分類、回答是或否，或為選項打分並給出機率。該系列包括 2B、4B、9B 和 27B 規格。
ollama run d3 " A customer says their card was charged twice. " --ask " Is this a billing issue? "
Linux 和 Windows 上的 Flint
Flint 現在除 macOS 外，還可在 Linux 和 Windows 上執行。
其他改進
流式 OpenAI Responses 和 Anthropic Messages 請求現在會報告生成失敗，而不是在部分輸出後靜默結束。
ollama launch 現在會將雲模型的上下文長度和能力傳遞給編碼工具，修復了不正確的上下文和壓縮設定。
相容 Anthropic 的網頁搜尋現在會在後續請求中使用模型支援的思考設定，從而防止可避免的失敗。
完整變更日誌：v0.40.8...v0.40.9
由 AI 翻譯，以原文為準。
原文
Speech
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 apps 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. Give a model text, structured state, or an image, and ask it to classify, answer yes or no, or score options with probabilities. The family includes 2B, 4B, 9B, and 27B sizes.
ollama run d3 " A customer says their card was charged twice. " --ask " Is this a billing issue? "
Flint on Linux and Windows
Flint 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 launch now passes 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.
Full Changelog : v0.40.8...v0.40.9