Try Liquid AI's open d1-3B decision model in Colab
Melvin Vivas · X post · 2026-10-19 · Open on X
Topics: LLM Fundamentals, Fine-tuning & Model Customization · Level: intermediate
Summary
Liquid AI released Open d1, two open-weight multimodal decision models: d1-3B (text + vision) and d1-omni-600M (text + image or text + audio). They are built for real-time decision making on hardware from DGX servers to Jetson edge devices. The creator shares a Colab notebook for trying d1-3B.
Key points
- Open d1 is Liquid AI's open-weight multimodal decision model family
- d1-3B handles text + vision
- d1-omni-600M handles text + image or text + audio
- Built for real-time decision making, from NVIDIA DGX data centers to RTX workstations to Jetson at the edge
- The creator's GitHub repo has Colab notebooks for running and fine-tuning local models
Resources mentioned
- donvito/notebooks · repo · github.com · free
The creator's notebooks for fine-tuning and running local models, which you can run in Google Colab, including a GLiNER2.5-Decide intent classification example.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try EmbeddingGemma 2 multimodal embeddings in Colab (Melvin Vivas on X · notes), Colab Notebook for Liquid AI's d1-3B Decision Model (Melvin Vivas on X · notes), Fine-tune and Run Local Models for Free on Google Colab's T4 GPU (Melvin Vivas on X · notes) and 10 more - Liquid AI (@liquidai) on X · website · x.com · free
Liquid AI's family of efficient foundation models, used here as the example of a model you can run in the browser with ONNX.
Also in: Trying Liquid AI Decision Models (d1, d1 ultra) via API (Melvin Vivas on X · notes), Liquid RIPL: Low-Latency Inference Engine for LFMs (Melvin Vivas on X · notes), ONNX + Transformers.js: Run Models Like Liquid LFM in the Browser (Melvin Vivas on X · notes), Liquid AI releases d1-ultra decision model (Melvin Vivas on X · notes) and 30 more - d1-3B · tool · huggingface.co · free
Open, small multimodal decision models from Liquid AI that can run locally and accept video input.
Also in: Colab Notebook for Liquid AI's d1-3B Decision Model (Melvin Vivas on X · notes), Testing Liquid AI d1-3B in Colab from a Phone (Melvin Vivas on X · notes), Liquid AI releases Open d1 open-weight multimodal decision models (Melvin Vivas on X · notes), Liquid AI's open d1 decision models: small multimodal models that run locally (Melvin Vivas on X · notes) - d1-omni-600M · tool · huggingface.co · free
Liquid AI's experimental small open-weight multimodal decision model for text with image or audio.
Also in: Liquid AI Open d1: d1-3B and d1-omni-600M Decision Models (Melvin Vivas on X · notes), Liquid AI releases Open d1 open-weight multimodal decision models (Melvin Vivas on X · notes) - Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
Free GPU notebooks.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Google Colab notebooks for new open models, built by a coding agent (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes), A100 80GB GPUs in Google Colab via Google AI Pro plans (Melvin Vivas on X · notes) and 27 more
Try this
- Open the creator's Colab notebook and run d1-3B
- A real-time vision-based decision demo using d1-3B on an edge device
More in LLM Fundamentals
- Decisions API: Low-Latency Model for Routing, Classification and Actions
- Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4
- Stealth Model 'Space Bunny' Revealed as MiniMax M3.1 Flash
- Muse Spark Open: Meta's 816B MoE Open-Weight Model Specs
- New Gemma Developer Documentation Site
- Grok Voice 3.0: xAI's Speech-to-Speech Model