{"id":"lfm3-vl-2b","slug":"lfm3-vl-2b","name":"LFM3-VL-2B","orgId":"liquid","family":"lfm3-vl-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"],"aliases":["LFM3-VL-2B","lfm3 vl 2b","lfm3-vl-2b","liquidai/lfm3-vl-2b","lfm3-vl"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-27","announced":"2026-10-27","blurb":"Liquid AI's LFM3 vision-language model for on-device use. It takes text, images and video (the first LFM vision model with video input), can reason step by step before answering, and localizes objects for spatial and embodied reasoning. Open weights under the LFM Open License v1.0.","api":"live","openWeights":"yes","params":{"text":"1.92B","source":"Hugging Face model card: 1.73B language model, 164M vision encoder, 25M projector"},"facts":[{"label":"Architecture","value":"LFM3 language model (24 layers) plus a new in-house vision encoder (14 layers: 8 gated depthwise 2D convolutions, 6 bidirectional attention)"},{"label":"Inputs","value":"Text, images and video at native resolution; video sampled at 2 fps"},{"label":"Context","value":"128K tokens (input + output)"},{"label":"Languages","value":"Same 16 text languages as LFM3-1.7B"},{"label":"License","value":"LFM Open License v1.0"},{"label":"API","value":"Liquid AI API and Playground, per Liquid's blog"}],"claims":["Lab claim: across 62 vision benchmarks it matches Gemma 4 12B, surpasses Gemini 3.5 Flash Lite, is within 2 points of GPT-5.6 Luna, and leads similar-size models by at least 7.4 points.","Lab claim: the new vision encoder uses 3x less compute than the SigLIP2 encoder in earlier LFM VL models."],"sources":[{"kind":"lab","title":"Liquid AI: Introducing LFM3","url":"https://www.liquid.ai/blog/lfm3","date":"2026-10-27"},{"kind":"repo","title":"LiquidAI/LFM3-VL-2B on Hugging Face","url":"https://huggingface.co/LiquidAI/LFM3-VL-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-VL-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":[]}