Jev Vision 2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.0 GB (Q2_K) to 3.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Jev Vision 2B – a 1.88B multimodal decision model
Jev Vision 2B is a 1.88B parameter model fine‑tuned from Qwen3.5‑2B for typed decisions over images, image sequences, GUI states, robotics/video frames, games, VQA, spatial tasks, and text. It performs one‑forward decision scoring with a state, question, and 2–26 options.
Good at
- Vision‑based decision making
- Typed choice and yes/no tasks
- Multimodal input handling
Limits
- No free‑form answer parsing
- Requires one‑forward inference
- No vision support beyond images
Best for
- GUI state evaluation
- VQA decision scoring
- Robotics frame analysis
Who it’s for. Developers building decision‑oriented multimodal applications. The model is suitable for tasks that require a single forward pass to score options, such as GUI testing, VQA, and robotics video analysis.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.9 GB | Fits | Get file → | |
| F16 | 3.8 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.27 GB, ~2.2 GB memory) or Q5_K_M (1.41 GB, ~2.3 GB memory). For 4 GB VRAM, choose Q3_K_M (1.10 GB, ~2 GB memory). Higher precision quants like F16 require more memory and are not recommended for low‑VRAM setups.
What GPU do you need for Jev Vision 2B?
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 Q8_0 (2.0 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.8 GB file, about 4.7 GB in use).
Which Jev Vision 2B quant should you choose?
Q4_K_M is the usual starting point for Jev Vision 2B: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.0 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 1.0 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 Jev Vision 2B
How much VRAM does Jev Vision 2B need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Vision 2B on an 8 GB GPU?
Yes, with F16: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jev Vision 2B GGUF?
It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.2 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB and 6 more.
What context length does Jev Vision 2B 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 1.7 GB at 32K.
Where can I download Jev Vision 2B GGUF?
The files are on Hugging Face in the mradermacher/Jev-Vision-2B-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 Vision 2B use?
Hugging Face lists the license as other. 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 Vision 2B on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quants will fit within 8 GB VRAM with approximate memory usage of 2.2–2.3 GB at 8k context.
Does the model support vision input?
Yes, it accepts zero to four images as part of the prompt and processes them with its vision tower.
Is there a free‑form answer mode?
No, the model requires typed decisions and does not parse free‑form answers.