{"id":"lfm3-omni-2b","slug":"lfm3-omni-2b","name":"LFM3-Omni-2B","orgId":"liquid","family":"lfm3-omni-2b","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":2000000000,"paramsSource":"slug","contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://www.liquid.ai/blog/lfm3","hfRepo":null,"modalities":["text","image","video","audio"],"aliases":["LFM3-Omni-2B","lfm3 omni 2b","lfm3-omni-2b","liquidai/lfm3-omni-2b","lfm3-omni"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-27","announced":"2026-10-27","blurb":"Liquid AI's first omni model: one on-device model that takes text, images, video with its soundtrack, and audio, and answers in text and speech, in place of separate speech recognition, vision-language, language and text-to-speech models. Open weights under the LFM Open License v1.0.","api":"live","openWeights":"yes","params":{"text":"2.17B","source":"Hugging Face model card (safetensors: 2,166,928,384)"},"facts":[{"label":"Architecture","value":"LFM3 backbone, LFM3 vision encoder, LFM3 causal audio encoder and LiquidCodec audio tokenizer"},{"label":"Inputs","value":"Text, images, video with or without its soundtrack (2 fps), and 16 kHz audio"},{"label":"Outputs","value":"Text, 24 kHz speech, or interleaved text and speech"},{"label":"Context","value":"32K tokens (input + output)"},{"label":"Reasoning","value":"Non-reasoning model (no thinking mode)"},{"label":"License","value":"LFM Open License v1.0"},{"label":"API","value":"Liquid AI API and Playground, per Liquid's blog"}],"claims":["Lab claim: 47.1 on WorldSense and 48.2 on OmniBench Speech, vs 45.4 and 48.0 for Qwen2.5-Omni-7B (10.7B)."],"sources":[{"kind":"lab","title":"Liquid AI: Introducing LFM3","url":"https://www.liquid.ai/blog/lfm3","date":"2026-10-27"},{"kind":"repo","title":"LiquidAI/LFM3-Omni-2B on Hugging Face","url":"https://huggingface.co/LiquidAI/LFM3-Omni-2B"}],"firstBenchmark":null},"organization":{"id":"liquid","name":"Liquid AI","slug":"liquid","country":null,"url":null,"color":"#1F6FEB","mark":"L"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 27, 2026; no independent results yet.","lead":"As of Nov 3, 2026, LFM3-Omni-2B is pending benchmarks on isitsota: announced Oct 27, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}