LFM3-VL-2BPreview
Compact 2B hybrid vision‑language model from Liquid AI built for on‑device image and text understanding.
LFM3‑VL‑2B is a vision‑language model in the LFM3 family of hybrid models designed for on‑device deployment. It processes text and images at their native resolution, and uses an LFM3 language model as its backbone, combined with a Liquid hybrid convolution/attention vision encoder.
Not supported
This model is currently not supported on any Compute chipset.
To see performance metrics for this model on other chipsets, click the button below.
View for other chipsetsTechnical Details
Parameters:2B (1.73B language model, 164M vision encoder, 25M projector)
Supported Input Modalities:image, text
Supported Output Modalities:text
model_infer_id:LiquidAI/LFM3-VL-2B-GGUF
Applicable Scenarios
- Dialogue
- Content Generation
License
Model:LFM1.0
Terms of Use:Qualcomm® Generative AI usage and limitations
Tags
- llm
- vlm
- generative-ai
Supported Compute Devices
- Snapdragon X Elite CRD
- Snapdragon X2 Elite CRD
Supported Compute Chipsets
- Snapdragon® X Elite
- Snapdragon® X2 Elite
Looking for more? See models created by industry leaders.
Discover Model Makers