Open d1
Liquid AI · Released 7 Oct 2026
Open-weight models in the d1 family for edge and local use: d1-3B (text and images) and d1-omni-600M (text plus image, or text plus audio). They return an answer in a single forward pass rather than generating tokens.
- Maker
- Liquid AI
- Release date
- 7 Oct 2026
- First seen
- 7 Oct 2026
- Access
- Weights on Hugging Face; docs for local runs, including llama.cpp and NVIDIA Jetson.
- Pricing (as publicly stated)
- Open weights; self-hosted. No hosted list price was stated in the announcement.
- Modalities
- text, images, audio
- Question types
- noul, choice, score
- Latency (as stated)
- Liquid AI said d1-3B answers a question in 8 ms on an NVIDIA GeForce RTX 4090, 16 ms on a Jetson AGX Thor, 26 ms on a Jetson AGX Orin, and 50 ms on a Jetson Orin Nano.
- Official announcement
- https://www.liquid.ai/blog/d1-open
Benchmark claims
These are claims as published by the maker or in the linked official post. We have not independently rerun every benchmark.
Liquid AI said d1-3B scored 48.57 on the Decision Index v0.2.1 public split, ahead of every model under 10B and on par with Decider 35B-A3B, a decision model 12x its size. It said d1-omni-600M scored 15.95 on the same index.
Names and marks belong to their owners. This page is an independent summary, not a product page from Liquid AI.