Liquid AI releases open d1 models for multimodal edge decisions

Liquid AI released d1-3B, an open-weight text-and-image decision model scoring an average 74.1 across 11 public image benchmarks, and the experimental d1-omni-600M for text paired with images or audio, on October 7th via Hugging Face. The models return structured outputs such as yes-or-no decisions, label selection and rubric-based scores in a single forward pass, giving developers a local alternative to API calls for routing, inspection and classification tasks. Liquid AI calls the models open-weight but states no license beyond the LFM 1.0 terms listed on both Hugging Face model cards.

Liquid AI releases open d1 models for multimodal edge decisions Liquid AI released d1-3B for text and images and an experimental 600M model that pairs text with images or audio. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: Hugging Face Newsroom https://huggingface.co/blog/LiquidAI/open-d1 Why it matters The open-weight releases give developers a local alternative to API calls for structured tasks. Liquid AI's d1-3B model card https://huggingface.co/LiquidAI/d1-3b?ref=runtimewire reports an average score of 74.1 across 11 public image benchmarks; the release gives no audio decision benchmark score. Liquid AI https://www.liquid.ai/?ref=runtimewire , co-founded by CEO Ramin Hasani https://www.liquid.ai/team/ramin-hasani?ref=runtimewire , released two open-weight models in its d1 decision family on October 7th. The Hugging Face release https://huggingface.co/blog/LiquidAI/open-d1?ref=runtimewire introduces d1-3B https://huggingface.co/LiquidAI/d1-3b?ref=runtimewire , which accepts text and images, and experimental d1-omni-600M https://huggingface.co/LiquidAI/d1-omni-600M?ref=runtimewire , which accepts text paired with either images or audio. Developers can download and run the models themselves, or try demos in Liquid AI's System One Arcade https://huggingface.co/spaces/LiquidAI/system-one-arcade?ref=runtimewire . Hasani has pursued the idea of building models that work within the limits of real devices since Liquid AI's founding in 2023. Before co-founding Liquid AI https://www.liquid.ai/?ref=runtimewire , Hasani was a CSAIL postdoctoral associate and a principal AI and machine-learning scientist at Vanguard. His research includes decision-making in complex systems, relevant to models designed to return a choice or score instead of composing an answer in prose. Liquid AI introduced an API-hosted d1 model in a company post on October 5th https://www.liquid.ai/blog/d1-decision-model?ref=runtimewire and said it planned to release open weights for upcoming models. Two days later, the Hugging Face post offered d1-3B https://runtimewire.com/models/huggingface/liquidai-d1-3b-fb3a1a604d63b0af and d1-omni-600M https://runtimewire.com/models/huggingface/liquidai-d1-omni-600m-cdfd8291328b2175 as open-weight downloads. Liquid AI is making separate decision-model checkpoints available for local deployment alongside its API. A model built to return a decision Generative models produce tokens, even for narrow tasks such as sorting a support ticket or deciding whether an image shows a defect. Liquid AI's decision models instead process a state in a single forward pass and return structured answers. The release describes yes-or-no decisions, label selection and rubric-based scores as supported outputs. That format could suit routing, inspection and classification tasks where software needs an answer it can act on, rather than a paragraph it must parse. The two models use different foundations. d1-3B is built on Liquid AI's LFM2.5-VL-3B https://runtimewire.com/models/huggingface/liquidai-lfm2.5-vl-3b-7f26099f5ddfe449 vision-language model. d1-omni-600M uses the LFM2.5-Encoder-350M bidirectional encoder, with added vision and audio encoders. Liquid AI labels the smaller model experimental and says it remains under development; it did not report speed numbers for it. The new downloads let developers evaluate local deployment, while the October 5th release described an API-hosted model. Liquid AI's announcement says both new models are available on Hugging Face and includes code showing d1-3B loaded through Transformers. It also instructs users to enable trust remote code=True . The release calls the models open-weight but does not state a license. Both Hugging Face model cards list LFM 1.0; teams evaluating deployment should review those terms for their intended use. Company-reported benchmarks and latency In its Hugging Face release https://huggingface.co/blog/LiquidAI/open-d1?ref=runtimewire , Liquid AI reports a Decision Index 0.2.1 score of 48.57 for d1-3B, above the listed 4B and 9B models and Decider 35B-A3B at 47.11. For a separate comparison across seven public datasets, Liquid AI reports average scores of 82.9 for d1-3B and 78.4 for d1-omni-600M. Those figures exceed the listed Decider 4B and 2B averages, respectively. The October 7th announcement's benchmark tables do not include vision or audio scores. The d1-3B model card https://huggingface.co/LiquidAI/d1-3b?ref=runtimewire separately reports an average score of 74.1 across 11 public image benchmarks, compared with 73.9 for its LFM2.5-VL-3B base model. Liquid AI says the Decision Index v0.3 vision split is private and that audio decision benchmarks remain an open problem. The latency figures are also company-reported. In the same release https://huggingface.co/blog/LiquidAI/open-d1?ref=runtimewire , Liquid AI reports that d1-3B answered one question in 16 milliseconds on a Jetson AGX Thor, 26 milliseconds on a Jetson AGX Orin and 50 milliseconds on a Jetson Orin Nano. On the Thor, the reported time for three questions was 20 milliseconds. These results are specific to the tested devices and workloads; they do not establish performance across other hardware or tasks. Liquid AI's d1 models extend its device strategy to structured decisions and let developers run models outside a hosted API. Whether their speed and quality hold up in production tasks remains to be tested, particularly for the experimental audio-capable model. Liquid AI said its $250 million Series A, announced in December 2024 and led by AMD, would support model development and edge and on-premise product readiness, according to its funding announcement https://www.liquid.ai/blog/we-raised-250m-to-scale-capable-and-efficient-general-purpose-ai?ref=runtimewire . The d1 release applies that stated goal to compact models that return machine-readable decisions locally. A separate Hugging Face benchmark https://huggingface.co/datasets/LocalLLaMA/typed-decisions/blame/main/README.md?ref=runtimewire tested d1 on September 30th across 400 cases and 2,000 decisions, reporting 0.742 accuracy; it did not directly replicate Liquid AI's seven-dataset comparison.