# Liquid AI's d1-3B brings multimodal models to the edge

> The new LFM2-based d1-3B is a compact vision-language model aimed at running decisions directly on-device.

Published by The Open Weights on Oct 7, 2026. Canonical: https://theopenweights.com/news/lfm2-d1-3b-ps8k

## Key facts

- Company: LiquidAI
- Model: LFM2 d1-3B
- Version: d1-3B
- Category: Vision-Language
- Modalities: Vision-Language
- License: Other (Open weights, commercial use allowed)
- Parameters: 3B
- Context window: 33K tokens
- Architecture: Lfm2VlForConditionalGeneration
- Precision: BF16
- Weights size: 6.2 GB
- Significance: notable
- Published: 2026-10-07
- Last verified: 2026-10-08
- Hugging Face: https://huggingface.co/LiquidAI/d1-3B
- Canonical URL: https://theopenweights.com/news/lfm2-d1-3b-ps8k

Liquid AI has introduced **d1-3B**, part of a new line of open multimodal "decision" models built on the company's LFM2 architecture and designed to run at the edge. At roughly 3 billion parameters, the model is small enough to deploy on constrained hardware while handling vision-language tasks, according to the company's [announcement on Hugging Face](https://huggingface.co/blog/LiquidAI/open-d1).

The pitch here is less about chasing frontier benchmarks and more about placement. By keeping the parameter count modest and targeting on-device inference, d1-3B is positioned for scenarios where sending data to the cloud is impractical — think robotics, cameras, and other latency- or privacy-sensitive applications that need to interpret images and text locally.

## Why it matters

The open-weights landscape has been dominated by ever-larger models, but a growing share of real-world demand sits at the opposite end: compact systems that run where the data is generated. A multimodal model in the 1B–7B range that can actually fit on edge hardware fills a practical gap.

- **Multimodal:** handles both vision and language inputs
- **Compact:** around 3B parameters, sized for edge deployment
- **Open:** weights published on Hugging Face under the company's license

Liquid AI frames d1 as a family rather than a one-off, suggesting more variants may follow. For developers building on-device applications, the release offers a lightweight option worth evaluating against existing small multimodal models. Full details are available in Liquid AI's [blog post](https://huggingface.co/blog/LiquidAI/open-d1).

## Get the model

- [Hugging Face](https://huggingface.co/LiquidAI/d1-3B)
- [Announcement](https://huggingface.co/blog/LiquidAI/open-d1)

## Sources

- [Multimodal open d1 decision models for the edge](https://huggingface.co/blog/LiquidAI/open-d1) — Announcement, Oct 7, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Liquid AI's d1-3B brings multimodal models to the edge", The Open Weights, Oct 7, 2026, https://theopenweights.com/news/lfm2-d1-3b-ps8k