MATRIX · Ollama https://derekwang2002.github.io/ai-intelligence/en/projects/ollama/ Material changes in AI models, agents, engineering and infrastructure, with primary sources and recommendations. en Mon, 02 Nov 2026 16:56:00 GMT Ollama 0.40.13 expands LFM3 audio and omni models to Linux and Windows https://derekwang2002.github.io/ai-intelligence/en/events/ev-20260928-09/ ev-20260928-09-ollama-0-40-13 Thu, 29 Oct 2026 16:05:08 GMT Update TRIAL <p>Ollama 0.40.13 expands LFM3 audio and omni models to Linux and Windows.</p><p>Original story: Ollama adds probability-first decision models for local routing</p><p>Recommendation: TRIAL</p><p>Sources: <a href="https://github.com/ollama/ollama/releases/tag/v0.40.13">Ollama 0.40.13 release</a></p> Ollama 0.40.9 adds local streaming speech on Apple Silicon https://derekwang2002.github.io/ai-intelligence/en/events/ev-20260928-09/ ev-20260928-09-ollama-0-40-9-speech Fri, 23 Oct 2026 16:04:55 GMT Update TRIAL <p>Ollama 0.40.9 adds local streaming speech on Apple Silicon</p><p>Original story: Ollama adds probability-first decision models for local routing</p><p>Recommendation: TRIAL</p><p>Sources: <a href="https://github.com/ollama/ollama/releases/tag/v0.40.9">Ollama 0.40.9</a> · <a href="https://ollama.com/library/phonon">Phonon model library</a></p> Ollama 0.35.1 lets clients recognize decision-model capability https://derekwang2002.github.io/ai-intelligence/en/events/ev-20260928-09/ ev-20260928-09-ollama-0-35-1 Sun, 04 Oct 2026 16:02:19 GMT Update TRIAL <p>Ollama 0.35.1 lets clients recognize decision-model capability</p><p>Original story: Ollama adds probability-first decision models for local routing</p><p>Recommendation: TRIAL</p><p>Sources: <a href="https://github.com/ollama/ollama/releases/tag/v0.35.1">Ollama 0.35.1</a></p> Ollama adds probability-first decision models for local routing https://derekwang2002.github.io/ai-intelligence/en/events/ev-20260928-09/ ev-20260928-09-published Thu, 01 Oct 2026 16:01:43 GMT New TRIAL <p>Ollama now serves local decision models, streaming speech paths and Liquid AI LFM3 models. Version 0.40.13 expands LFM3, including lfm3-audio text-to-speech and lfm3-omni, from Apple silicon to Linux and Windows. Model quality, hardware-specific latency and individual model licenses still require workload review.</p><p>Recommendation: TRIAL</p><p>Sources: <a href="https://github.com/ollama/ollama/releases/tag/v0.35.0">ollama/ollama · releases / tag / v0.35.0</a></p>