metadata
license: other
license_name: lfm1.0
license_link: LICENSE
language:
- en
- ja
- fr
- es
- de
- it
- pt
- ar
- zh
- ko
pipeline_tag: image-text-to-text
tags:
- vision
- vlm
- liquid
- lfm2
- lfm2-vl
- edge
- llama.cpp
- gguf
base_model:
- LiquidAI/LFM2-VL-3B
LFM2-VL-3B-GGUF
LFM2-VL is a new generation of vision models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.
Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2-VL-3B
🏃 How to run LFM2-VL
Example usage with llama.cpp:
full precision (F16/F16):
llama-mtmd-cli -hf LiquidAI/LFM2-VL-3B-GGUF:F16
fastest inference (Q4_0/Q8_0):
llama-mtmd-cli -hf LiquidAI/LFM2-VL-3B-GGUF:Q4_0