Jev-Omni
Jev-Omni is an open-weight multimodal decision classifier built on Gemma 4 12B IT and fine-tuned on 30,000 questions. It returns probabilities for supplied options rather than generating an explanation.
What it does
A person can use it to classify decisions across text, images, audio, and video by comparing probabilities for provided options.
- Availability
- Quick start instructions and downloadable model on Hugging Face
- Pricing model
- No model price stated; cost estimate uses OpenRouter's Gemma 3 12B input rate
- Deployment
- CUDA GPU required; FP32 weights use about 50 GB before runtime overhead
- Privacy
- Not established
- Licence
- Apache-2.0, following Gemma 4
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- Jev-Omni supports text, image, audio, and video inputs. [1]
| **Jev-Omni** | 12B | **63.10%** | **53.10%** | Text, image, audio, video |
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - It returns a probability for each option and does not generate an explanation. [1]
Supply a question and options; receive a probability for each option—not a generated explanation.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The quick start downloads the model from Hugging Face using snapshot_download. [1]
- A CUDA GPU is required. [1]
- The model is best supported at 20 or fewer options; quality above 20 is not established. [1]
The head accepts 256, but quality above 20 is not established.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is licensed under Apache-2.0, following Gemma 4. [1]
**Apache-2.0**, following [Gemma 4](https://huggingface.co/google/gemma-4-12B-it).
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/akhilaaa3/Jev-Omni
Retrieved 2026-10-29 00:34 UTC
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-21 10:34 UTC | evidence update | score | Current |
| 2 | 2026-09-29 07:16 UTC | material change | pricing, availability | Current |
| 1 | 2026-09-28 08:08 UTC | publication | None | Current |
In briefs
1- ElevenLabs introduces two text-to-speech models Daily brief 2026-09-28
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.