LFM3-VL-2B is a **vision-language model for on-device visual understanding.** It takes text, images, and video (soon) as input, and combines the LFM3 language model with a new in-house vision encoder…
LFM3-VL-2B is a **vision-language model for on-device visual understanding.** It takes text, images, and video (soon) as input, and combines the LFM3 language model with a new in-house vision encoder.
New in LFM3-VL-2B:
* **Video understanding (soon):** the first LFM vision model that takes video as input. Ask questions about a recorded lecture, a walkthrough filmed on your phone, or a clip from a camera feed.
* **Thinking:** the model reasons step by step before it answers. This helps most with harder visual questions, such as math, charts, and multi-step problems.
* **Spatial and embodied reasoning:** the model finds objects and reasons about how they are placed relative to each other, a strong foundation for robotics applications.
# Model details
The LFM3 family includes base, text, vision, audio, omni, and decision models.
| Property | Specification |
|:--- |:---:|
| Checkpoint | Post-trained vision-language model |
| Parameters | 1.92B: 1.73B language model, 164M vision encoder, 25M projector |
| Architecture | LFM3, 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
| Vision encoder | 14 layers: 8 gated depthwise 2D convolutions, 6 bidirectional attention, 16×16 patches with 2D rotary embeddings
| Inputs | Text, images, and video (soon) at native resolution. Each 2×2 block of patches becomes one language token. Video is sampled at 2 fps.
| Context length| 128K tokens (input + output)
| Vocabulary | 128,000 tokens
| Languages | English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish
| License | LFM Open License v1.0
LFM3-VL-2B is designed for on-device visual tasks: questions about video, reading documents, charts, and app screens, finding objects in an image, and spatial reasoning for robots. It is not recommended for coding, multi-turn conversations, or complex reasoning.