Liquid AI releases Open d1 open-weight multimodal decision models
Melvin Vivas · X post · 2026-10-08 · Open on X
Topics: LLM Fundamentals, Industry Trends & Job Market · Level: intermediate
Summary
Melvin Vivas shares Liquid AI's release of Open d1, two open-weight multimodal decision models. d1-3B handles text and vision; d1-omni-600M handles text with image or audio. Liquid AI targets real-time decision making from data centers down to edge devices.
Key points
- Open d1 includes two open-weight models in Liquid AI's d1 decision model family.
- d1-3B: text + vision.
- d1-omni-600M: text + image, or text + audio.
- Built for real-time decisions on NVIDIA hardware, from DGX in data centers to RTX workstations to Jetson at the edge.
Resources mentioned
- d1-3B · tool · huggingface.co · free
Open, small multimodal decision models from Liquid AI that can run locally and accept video input.
Also in: Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), 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'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: Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Liquid AI Open d1: d1-3B and d1-omni-600M Decision Models (Melvin Vivas on X · notes) - NVIDIA Jetson · tool · developer.nvidia.com · paid
NVIDIA's edge AI computing platform for running models on devices.
Try this
- Try the Open d1 models (the creator says he will give them a spin).
More in LLM Fundamentals
- Colab Notebook for Liquid AI's d1-3B Decision Model
- Testing Liquid AI d1-3B in Colab from a Phone
- Liquid AI Open d1: d1-3B and d1-omni-600M Decision Models
- Claude Haiku 5.5 in Devin: beats Sonnet 5 at about 1/8 the cost
- Liquid AI's open d1 decision models: small multimodal models that run locally
- Comparing Opus 5.5, GPT-6 Astra and Grok 4.7 on OpenRouter