Ollama released v0.40.12 on October 27, 2026. The release adds Liquid AI's new LFM3 model family and a 2B size of the d1 decision models. Read the release notes.
The LFM3 family
LFM3 is Liquid AI's family of small models built for local agents, tool calling and structured output, on Liquid's new tri-hybrid architecture:
- lfm3: a 1.7B text model with a 256K-token context window.
- lfm3-vl: adds image understanding.
- lfm3-audio: speech recognition, translation and text-to-speech in 18 languages.
- lfm3-omni: text, images and audio in one model.
ollama run lfm3d1 at 2B
Liquid AI's d1 decision models now come in a 2B size built on LFM3. d1 makes decisions about text and images, and d1-omni adds audio:
ollama run d1:2b "I was charged twice for order 4417." --ask "Is this a billing issue?"The release notes state that lfm3 and d1 2B are supported on Apple hardware in this release, with Linux and Windows support coming soon.
Other changes
- Faster prompt processing on Apple silicon for Gemma 4, Flint and Laguna models.
- Speculative decoding now supports DFlash2 draft models on MLX.
- Gemma 4 keeps more detail in small images.
ollama launchnow works with OpenCode v2, and tool-only assistant turns from Kimi CLI are fixed.- MLX and llama.cpp were updated.
This report covers the October 27 release notes; the previous release is covered in our v0.40.11 report.