Liquid AI’s LFM2-VL-450M: Vision-Language AI in Half a Billion Parameters

Liquid AI has released LFM2-VL-450M, a 450-million-parameter vision-language model designed for on-device inference. Built on Liquid’s LFM2-350M language backbone and an 86M-parameter SigLIP2 NaFlex vision encoder, the model delivers 2× faster inference than comparable VLMs on GPUs while processing images at native resolution — all under an Apache 2.0 license.

Intermediate

Architecture

LFM2-VL-450M combines three components:

• Language tower: LFM2-350M, Liquid AI’s compact language backbone based on their proprietary Liquid Foundation Model architecture
• Vision tower: SigLIP2 NaFlex encoder (86M parameters, base variant) for fast image processing
• Multimodal projector: A 2-layer MLP with pixel unshuffle for token reduction

The vision encoder processes images at their native resolution up to 512×512 pixels without upscaling, and handles non-standard aspect ratios without distortion. Larger images are split into non-overlapping 512×512 patches. A 256×384 image generates approximately 96 visual tokens — keeping the context budget lean for on-device use.

Performance

Despite its tiny parameter count, LFM2-VL-450M posts competitive benchmark numbers:

• OCRBench: 655 — strong document understanding for a sub-500M model
• SEEDBench_IMG: 63.5 — solid image understanding
• RealWorldQA: 52.29 — practical visual reasoning
• Inference speed: 2× faster than comparable VLMs on GPU

The model features user-tunable speed-quality tradeoffs at inference time, allowing developers to optimize for their specific latency and accuracy requirements. It was trained on approximately 100 billion multimodal tokens.

What This Means

At 450 million parameters, LFM2-VL sits in a class of models designed to run directly on smartphones and edge devices. While larger VLMs like Qwen-VL and LLaVA dominate benchmarks, they require server-grade hardware. Liquid AI’s bet is that many vision-language tasks — OCR, document scanning, visual QA — don’t need a 7B+ model. The Apache 2.0 license and GGUF availability on Hugging Face make it easy to integrate into mobile and embedded applications.
This post was drafted with AI assistance and reviewed by RITS staff.

Sources

• LFM2-VL: Efficient Vision-Language Models — Liquid AI Blog
• LFM2-VL-450M on HuggingFace
• Liquid AI wants to give smartphones AI that can see — VentureBeat