OneJev 4B needs about 4.6 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 9 quants, from 2.5 GB (Q3_K_M) to 9.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
OneJev 4B – a 4.84B multimodal decision model
OneJev 4B is a 4.84B‑parameter multimodal model based on Qwen3.5. It accepts images, video, or text and returns calibrated probabilities for each option in a single forward pass. The model is fine‑tuned on 99,193 real‑world questions.
Good at
- Fast inference – 10 questions in 104 ms on H200
- Calibrated probability outputs
- Multimodal input support
Limits
- No text generation
- Requires 8 k context for estimates
- License is Apache‑2.0
Best for
- Decision‑making assistants
- Rapid question answering
- Multimodal probability estimation
Who it’s for. Developers building decision‑making systems that need quick, calibrated responses from images or text. It is suitable for applications requiring no text generation and a lightweight multimodal model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_L | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_S | 2.9 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.4 GB | 5.0 GB | Fits | Get file → | |
| Q5_K_M | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q6_K | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q8_0 | 5.2 GB | 6.7 GB | Fits | Get file → | |
| BF16 | 9.7 GB | 11.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 3.07 GB, estimated 4.6 GB memory). For 12 GB VRAM, Q5_K_M (3.51 GB, 5.1 GB memory) is a good balance. For larger GPUs, Q8_0 (5.16 GB, 6.7 GB memory) offers higher precision.
What GPU do you need for OneJev 4B?
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: the best quant that fits is Q6_K (4.0 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.2 GB file, about 6.7 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (9.7 GB file, about 11.3 GB in use).
Which OneJev 4B quant should you choose?
Q4_K_M is the usual starting point for OneJev 4B: it balances file size and quality well. Here it is a 3.1 GB file.
The Q8_0 file is 5.2 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 Q3_K_M at 2.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OneJev 4B
How much VRAM does OneJev 4B need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.1 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 OneJev 4B on an 8 GB GPU?
Yes, with Q8_0: the 5.2 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of OneJev 4B GGUF?
It depends on the quant: Q3_K_M is 2.5 GB, Q3_K_L is 2.7 GB, Q4_K_S is 2.9 GB, Q4_K_M is 3.1 GB, Q5_K_S is 3.4 GB, Q5_K_M is 3.5 GB and 3 more.
What context length does OneJev 4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download OneJev 4B GGUF?
The files are on Hugging Face in the prithivMLmods/OneJev-4B-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 OneJev 4B 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 OneJev 4B on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 4.6 GB of VRAM at 8 k context, which fits in 8 GB.
Does OneJev 4B support text generation?
No, it returns calibrated probabilities only and does not generate text.