Cloudflare/clef-omni
image-text-to-text model by Cloudflare
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.
Clef-Omni is a 30B-A3B mixture-of-experts multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, audio, or video, and returns a probability for every allowed option of every question in a single forward pass. There is no free-form text generation and no output parsing. The Clef-Omni API is fully compatible with Jev and SystemOne. Clef-Omni is post-trained from Qwen/Qwen3-Omni-30B-A3B-Instruct. See Clef and Clef-Flash for the dense image and video variants. as standard sharded safetensors. The base model's speech-output weights (talker and code2wav) are included unchanged but are not used; loadreleasemodel does not load them. routes evidence from the state to each question, and scores all options of all questions jointly. probabilities. Tested with torch 2.11 and transformers 5.10.2 on a single H200; the backbone needs about 64 GB of GPU memory in bfloat16. Image inputs also need pillow,…
Read the full model card ↗ · Preview checked 2026-11-01T04:06:37.206Z
Inside the original model card — Document outline
- Clef-Omni
- Model
- Files
- Usage
- Jev / SystemOne API
- Images, audio, and video
- SGLang
- Input format
- Results
- Decision Index
- Workflow evals
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
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
Cloudflare/clef-omni is a image-text-to-text model repository published by Cloudflare 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
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 3,650
- Cumulative likes
- 126
- Hugging Face trending score
- 90
- Reported safetensors parameters
- 35,259,818,545
- Architecture
- Qwen3OmniMoeForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-09T04:10:22.000Z
- Last modified
- 2026-10-09T17:49:32.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3-Omni-30B-A3B-Instruct
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 2026-10-17T06:41:56.108Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.