Ollama v0.40.12 adds support for Liquid AI LFM3 and d1 models
Ollama v0.40.12 adds support for Liquid AI’s LFM3 family and 2B d1 decision models. The release notes describe lfm3 as a 1.7B text model with a 256K-token context window, lfm3-vl as adding image understanding, lfm3-audio as supporting speech recognition, translation and text-to-speech in 18 languages, and lfm3-omni as combining text, images and audio. The d1 models make decisions about text and images, while d1-omni adds audio. The release notes state that lfm3 and d1 2b are supported on Apple hardware, with Linux and Windows support described as coming soon.
The release notes position the models for local agents, tool calling, structured output and multimodal workloads, and make the LFM3 and d1 model families available through Ollama on Apple hardware.
Liquid AI LFM3
LFM3 is Liquid AI's new family of small models built for local agents, tool calling, and structured output, on Liquid's new tri-hybrid architecture. The family includes:
- 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 decision models
Liquid AI's d1 models now come in a 2B size, built on LFM3. d1 makes decisions about text and images, and d1-omni adds audio.
#Ollama#Liquid AI#LFM3#lfm3-vl#lfm3-audio#lfm3-omni#d1#d1-omni