Jev-Omni needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 0.0 GB to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Jev-Omni – a multimodal decision classifier for text, images, audio and video
Jev-Omni is a multimodal decision classifier built on Gemma 4 12B IT. It accepts a state, a question, and answer options and returns calibrated probabilities for each option. The model supports up to 256 options, with quality best established for up to 20 options.
Good at
- Calibrated probability outputs
- Multimodal input handling
- Fast inference on CUDA GPUs
Limits
- Best quality up to 20 options
- Long‑context behavior not validated
- Requires CUDA GPU for inference
Best for
- Decision‑making tasks with multiple choice
- Rapid multimodal classification
- Low‑latency inference on GPUs
Who it’s for. Developers and researchers needing a lightweight decision classifier that can process text, images, audio and video. The model is useful for applications that require probability scores rather than generated text.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 13.4 GB | Too big | Get file → | |
| Q1_0 | 2.4 GB | 15.8 GB | Too big | Get file → | |
| IQ1_M | 3.2 GB | 16.6 GB | Too big | Get file → | |
| IQ2_XS | 3.9 GB | 17.3 GB | Too big | Get file → | |
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (7.38 GB file, 20.8 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (8.55 GB file, 21.9 GB memory) or Q6_K (9.79 GB file, 23.2 GB memory) are suitable. For 16 GB VRAM, Q8_0 (12.67 GB file, 26.1 GB memory) provides the highest precision.
What GPU do you need for Jev-Omni?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q1_0 (2.4 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which Jev-Omni quant should you choose?
Q4_K_M is the usual starting point for Jev-Omni: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jev-Omni
How much VRAM does Jev-Omni need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Jev-Omni on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jev-Omni GGUF?
It depends on the quant: file is 0.0 GB, Q1_0 is 2.4 GB, IQ1_M is 3.2 GB, IQ2_XS is 3.9 GB, Q2_K is 4.8 GB, Q3_K_M is 6.1 GB and 4 more.
What context length does Jev-Omni support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download Jev-Omni GGUF?
The files are on Hugging Face in the ngquocvinh/Jev-Omni-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Jev-Omni use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Jev-Omni on 8 GB VRAM?
Yes, the Q4_K_M quantization requires 7.38 GB file size and approximately 20.8 GB memory at 8 k context, which fits within 8 GB VRAM with offload.
Does Jev-Omni support video input?
Yes, the model accepts video input with 16 frames and audio capped at 30 seconds.
What license applies to Jev-Omni?
The model is licensed under Apache-2.0, following Gemma 4.