Liquid AI releases the LFM3 family of foundation models covering text, audio, vision and omni modalities for on-device use
Liquid AI released LFM3 on October 27. Six 2B-class models share the LFM3-1.7B-Base backbone: text LFM3-1.7B, LFM3-VL-2B with video input, LFM3-Audio-2B, its first omni model LFM3-Omni-2B, and decision models d1-2B and d1-omni-2B. Weights are on Hugging Face under Liquid's custom lfm1.0 license; Liquid says the 4-bit text model is ~1 GB with 256K context and each model fine-tunes on one GPU.
Why it matters
On-device small models are moving beyond text; LFM3 targets local fine-tuning and phones or laptops. Claims like 1.7B beating the prior 2.6B are Liquid's own, and the custom license is not Apache or MIT.
Sources6
Liquid AIMediaIntroducing LFM3: Every Modality for Specialized IntelligenceView original ·
Hugging Face · LiquidAIMediaBuild specialized multimodal models with LFM3View original ·
- @liquidaiXIntroducing 𝙻𝙵𝙼𝟹: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence. > 6 model instances, across text, audio, vision, and omni modalities, generative and decision models. > 𝙻𝙵𝙼𝟹-𝟷.𝟽𝙱: text, 256k context window. > 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱: vision-language model with video-input support for spatial understanding > 𝙻𝙵𝙼𝟹-𝙰𝚞𝚍𝚒𝚘-𝟸𝙱: tool calls, voice chat, reasoning in 18 languages. > 𝙻𝙵𝙼𝟹-𝙾𝚖𝚗𝚒-𝟸𝙱: an omni model combines vision, audio, and language. > 𝚍𝟷-𝟸𝙱 and 𝚍𝟷-𝙾𝚖𝚗𝚒-𝟸𝙱: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input. > fine-tune on 1 GPU. > a new tri-hybrid architecture > architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs. > 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱 is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, andView original ·
- @lmstudioXLFM3 is live in LM Studio! Fits in about 1 GB of memory. Model page: lmstudio.ai/models/lfm3 x.com/liquidai/statu…View original ·
- @xenovacomXNEW: Liquid AI just released LFM3 on Hugging Face. The model family brings text, vision, audio, omni, and decision models together on a new shared backbone (~2B params). It can even do real-time video captioning locally in your browser on WebGPU with 🤗 Transformers.js!View original ·
- @ollamaXLFM3 from @liquidai is on Ollama! Small models built to run anywhere and fine-tune on a single GPU: - Text, vision, audio, omni, and decision models - Text model fits in about 1 GB at 4-bit - 256K context window Available to run locally.View original ·
Written by dalao.ai: the title, summary and why it matters are our own words. The original reports are the record; their publishers keep authorship.