LFM2 VL

Name: LFM2 VL
Author: Liquid AI

Liquid AIOpen WeightsPending Human Review

LFM2 VL extends Liquid AI’s efficient language architecture to image understanding. The original 450M and 1.6B models connect SigLIP2 NaFlex vision encoders to LFM2 backbones through a compact projector, supporting variable image shapes and document or scene questions. A larger 3B checkpoint followed on October 22. This page groups routine sizes while preserving the later checkpoint’s own chronology. Downloadable weights use Liquid’s custom license; local inference supports privacy and edge deployment. Image resolution and patch counts affect speed, memory, and visual detail.

2025-08-12

450M, 1.6B; later 3B

Hybrid short-convolution and attention with vision encoder

Liquid Open Model License 1.0

Compare with other models

Specifications

Parameters: 450M, 1.6B; later 3B
Architecture: Hybrid short-convolution and attention with vision encoder
License: Liquid Open Model License 1.0
Context Window: 32,768 tokens
Type: multimodal
Modalities: textimage

Benchmark Scores

Advanced Specifications

Model Family: LFM
API Access: Not Available
Chat Interface: Not Available
Variants: LFM2-VL-450MLFM2-VL-1.6BLFM2-VL-3B (2025-10-22)

Capabilities & Limitations

Capabilities: image understandingvisual questionslocal inference
Known Limitations: Original vision generation is deprecatedCustom commercial license conditions applyImage resolution settings trade speed for detail
Notable Use Cases: edge visual assistantsdocument interpretationprivate image analysis

Resources

Related Models

LFM2.5 VL 3B

Liquid AI

Liquid’s larger LFM2.5 vision model integrates a 400M SigLIP2 NaFlex encoder with the 2.6B language backbone. It strengthens screen understanding, grounding, multi-image processing, and function calling. The post-trained model answers directly without long reasoning traces, making it suitable for interactive visual assistants. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.

LFM2.5 2.6B

Liquid AI

This dense agent model scales pretraining to about 34T tokens and adds a dedicated 128K context-extension phase. Post-training combines teacher specialization, on-policy distillation, and reinforcement learning for planning and chained tool calls. The model is designed for smartphones, CPUs, and GPU serving, with downloadable base and post-trained checkpoints. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.

LFM2.5 230M

Liquid AI

Liquid’s smallest LFM2.5 text tier is designed for inexpensive local inference and downstream fine-tuning. Its training includes 19T tokens and a 32K context extension, followed by distillation, preference optimization, and reinforcement learning. It can select tools from natural-language instructions, but demonstrations of robot control rely on external low-level skills. Downloadable weights use the Liquid Open Model License, whose commercial-use conditions should be checked before deployment. Local inference supports private customization, while task reliability and performance require evaluation on the intended hardware.