# Liquid AI releases d1-3B decision model on Hugging Face

> The d1-3B model can answer typed questions over text, JSON or images in a single pass, without generating tokens.

Oossa · 2026-10-07 · https://oossa.com/en/liquid-ai-releases-d1-3b-decision-model-on-hugging-face

Liquid AI added a new model called d1-3B to Hugging Face. The model answers named, typed questions over a state that can be text, JSON or images, and it does so in one forward pass without generating tokens. Users can run it with llama.cpp and query it via a /v1/systemone HTTP endpoint. Example calls show how it handles a billing‑refund request and how it identifies cats in a photo.

## The facts

- Model name: LiquidAI/d1-3B-GGUF
- Published on Hugging Face: 2026-10-06

## Why it matters

Developers can integrate fast, token‑free question answering into support bots or image‑based workflows without needing large language model generation.

## Sources & references

1. [New model on Hugging Face: LiquidAI/d1-3B-GGUF (image-text-to-text)](https://huggingface.co/LiquidAI/d1-3B-GGUF) – Liquid AI, 2026-10-06
2. [New model on Hugging Face: LiquidAI/d1-omni-600M (image-text-to-text)](https://huggingface.co/LiquidAI/d1-omni-600M) – Liquid AI, 2026-10-05
3. [New model on Hugging Face: LiquidAI/d1-3B (image-text-to-text)](https://huggingface.co/LiquidAI/d1-3B) – Liquid AI, 2026-10-05
4. [Open d1: Edge decision models for text, vision, and audio](https://www.liquid.ai/blog/d1-open) – Liquid AI, 2026-10-07
5. [Multimodal open d1 decision models for the edge](https://huggingface.co/blog/LiquidAI/open-d1) – Hugging Face, 2026-10-07
6. [Liquid AI Releases Open-Weight d1-3B and d1-omni-600M: Multimodal Decision Models With Zero Output Tokens](https://www.marktechpost.com/2026/10/07/liquid-ai-releases-open-weight-d1-3b-and-d1-omni-600m-multimodal-decision-models-with-zero-output-tokens/) – MarkTechPost, 2026-10-07
7. [New model on Hugging Face: LiquidAI/d1-3B-w8a8 (image-text-to-text)](https://huggingface.co/LiquidAI/d1-3B-w8a8) – Liquid AI, 2026-10-07
8. [ggml-org/llama.cpp b11483](https://github.com/ggml-org/llama.cpp/releases/tag/b11483) – llama.cpp, 2026-10-08

Last updated: 2026-10-08