LFM3-VL-2B
MultimodalLFM3-VL-2B is Liquid AI's open-weight 1.92B vision-language model: a 1.73B LFM3 language backbone plus a new 164M in-house convolution/attention vision encoder and a 25M projector, released on October 27, 2026 as part of the LFM3 family. It accepts text, images and video (the first LFM model with video input, sampled at 2 fps) and answers in text, with a thinking mode used for the published scores. Trained on 22T tokens, published under the LFM Open License v1.0, with weights on Hugging Face for llama.cpp, MLX, vLLM and ONNX.
Key Specifications
Timeline
Technical Specifications
Benchmark Results
Model performance metrics across various tests and benchmarks
Multimodal
Other Tests
License & Metadata
Compare LFM3-VL-2B
All comparisonsSimilar Models
All ModelsLFM2.5-VL-3B
Liquid AI
Pixtral Large
Mistral AI
MiMo-V2.5
Xiaomi
LongCat-2.5
Meituan
MiniMax M2.5
MiniMax
GLM-5.3 Flash
Zhipu AI
Inkling
Thinking Machines Lab
MiMo-V2.6-Pro
Xiaomi
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.