thesysdev/OUI-1
text-generation model by thesysdev
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
OUI-1 is the first diffusion model built for generative UI. It is a finetune of Google's DiffusionGemma 26B-A4B-it that writes user interface screens in openui-lang, the declarative UI language behind OpenUI. It scores 71.7% on Generative UI Benchmark, 5.5x its base model, with 4B active parameters. Given a component library's signatures in the system prompt and a plain-language brief, it returns the screen as code, one component per line, wired into a root. Any component library with signatures can be the prompt, and any OpenUI app can point at it. Generative UI is unusually sensitive to latency, and this is a text diffusion model: it writes a 256-token block at once, starting from noise and committing each token the moment it is sure of it, so a screen arrives in about a second on one GPU. The generative-ui-bench protocol: 46 screen briefs in five size bands, 4 generations each, thinking…
Read the full model card ↗ · Preview checked 2026-10-30T15:59:57.524Z
Inside the original model card — Document outline
- OUI-1
- Results on the Generative UI Benchmark
- How to use
- vLLM (recommended)
- Function calling
- Transformers
- Adapter
- Intended use
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
thesysdev/OUI-1 is a text-generation model repository published by thesysdev on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 2,187
- Cumulative likes
- 126
- Hugging Face trending score
- 77
- Reported safetensors parameters
- 25,823,778,864
- Architecture
- DiffusionGemmaForBlockDiffusion
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-07T15:11:21.000Z
- Last modified
- 2026-09-11T06:49:16.000Z
Compatibility and lineage
Reported languages: en
Reported base models: google/diffusiongemma-26B-A4B-it
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-18T06:35:08.044Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.