Liquid AI releases Pareto-frontier, multimodal decision model for the edge
Liquid AI has released d1-3B and d1-omni-600M, two open-weight decision models designed for efficient multimodal inference on edge devices. The d1-3B model achieves performance comparable to much larger models while operating in milliseconds on standard NVIDIA hardware. These models are available on Hugging Face and support text, vision, and audio inputs through distinct architectural approaches.
- ▪d1-3B scores 48.57 on the Decision Index v0.2.1, outperforming all models under 10B parameters.
- ▪The d1-3B model processes queries in 8 ms on an RTX 4090 and 50 ms on a Jetson Orin Nano.
- ▪d1-omni-600M is an experimental checkpoint that handles text, image, and audio modalities using a bidirectional encoder backbone.
- ▪Both models are released as open weights and are available for download on Hugging Face.
Hacker News (AI / LLM) files mainly under ai. We currently carry 7,824 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Liquid AI |
| Canonical URL | https://www.liquid.ai/blog/d1-open |
| Publication time | Thu, 08 Oct 2026 01:01:06 +0000 |
| Retrieval time | 2026-10-08T01:08:22.091Z |
| Last seen | 2026-10-08T01:08:22.091Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | nrDA3dnZCe1m · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"News","item":"https://www.liquid.ai/news"},{"@type":"ListItem","position":2,"name":"Models","item":"https://www.liquid.ai/news/models"},{"@type":"ListItem","position":3,"name":"Open d1: Edge decision models for text, vision, and audio","item":"https://www.liquid.ai/blog/d1-open"}]}News/ModelsOpen d1: Edge decision models for text, vision, and audioOCT 7, 2026On this pageArchitecture and TrainingBenchmarksFast Inference EverywhereOpen d1 in ActionGet StartedCitationToday, we release d1-3B and d1-omni-600M, two open-weight models in our d1 decision model family.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Liquid AI.
Discussion
0 commentsMore from Liquid AI
