OneJev 0.8B needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.5 GB (Q2_K) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
OneJev 0.8B – a multimodal decision model for image and text
OneJev 0.8B is a 1.01B‑parameter model based on Qwen/Qwen3.5-0.8B. It returns calibrated probabilities for multiple options in a single forward pass. The model supports vision and runs on llama.cpp without PyTorch.
Good at
- Fast inference on images and text
- Calibrated probability outputs
- Single‑pass multi‑question handling
Limits
- No vision support in PyTorch server
- Large context requires high VRAM
- License is Apache‑2.0
Best for
- Rapid prototyping of multimodal decision systems
- Evaluating image‑based question answering
- Low‑latency inference on modest GPUs
Who it’s for. Developers building multimodal agents that need quick, probability‑based responses. Researchers testing vision‑enabled LLMs on small hardware. Teams deploying lightweight decision models in production.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 2.0 GB | Fits | Get file → | |
| F16 | 2.0 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_S (0.65 GB) or Q4_K_M (0.67 GB) – memory usage is about 1.6 GB at 8 k context. If more VRAM is available, Q5_K_M (0.75 GB) or Q6_K (0.84 GB) give higher quality. The F16 quant (2.03 GB) requires at least 2.9 GB VRAM.
What GPU do you need for OneJev 0.8B?
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: the best quant that fits is F16 (2.0 GB file, about 2.9 GB in use).
Which OneJev 0.8B quant should you choose?
Q4_K_M is the usual starting point for OneJev 0.8B: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.1 GB, about 1.6 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 Q2_K at 0.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OneJev 0.8B
How much VRAM does OneJev 0.8B need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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 0.8B on an 8 GB GPU?
Yes, with F16: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of OneJev 0.8B GGUF?
It depends on the quant: Q2_K is 0.5 GB, Q3_K_S is 0.5 GB, Q3_K_M is 0.6 GB, Q3_K_L is 0.6 GB, IQ4_XS is 0.6 GB, Q4_K_S is 0.6 GB and 6 more.
What context length does OneJev 0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download OneJev 0.8B GGUF?
The files are on Hugging Face in the mradermacher/OneJev-0.8B-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 0.8B 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 0.8B on 8 GB VRAM?
Yes, using Q4_K_S or Q4_K_M quantizations. They use about 1.6 GB of VRAM at 8 k context, leaving headroom for the model.
Does the model support video input?
Video input works only with the PyTorch server; llama.cpp supports images but not video.
What license applies to this model?
The model is released under the Apache‑2.0 license.