Cloudflare/clef
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 is a 27B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, 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 API is fully compatible with Jev and SystemOne. Clef is post-trained from Qwen/Qwen3.8-27B. See Clef-Flash for the smaller, faster variant. 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. Image and video inputs also need pillow. Clef can be served with SGLang. See the SGLang cookbook for launch commands on H200, B200, and B300. On a single H200: The server answers Jev/SystemOne requests at /v1/systemone: systemone takes a Jev/SystemOne POST /v1/systemone request body and returns…
Read the full model card ↗ · Preview checked 2026-11-15T00:28:19.952Z
Inside the original model card — Document outline
- Clef
- Model
- Files
- Usage
- SGLang
- Jev / SystemOne API
- Images and video
- 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.
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
Cloudflare/clef 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)
- 24,097
- Cumulative likes
- 2,267
- Hugging Face trending score
- 57
- Reported safetensors parameters
- 27,356,728,560
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-30T21:15:35.000Z
- Last modified
- 2026-10-19T15:07:45.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-27B
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 2026-10-25T06:45:38.398Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.