Decider 2b Vision 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 1.6 GB.
Decider 2b Vision – a 1.88B parameter vision‑language model for single‑slot multiple‑choice tasks
Decider 2b Vision is a 1.88B parameter Qwen3.5‑2B vision‑language model fine‑tuned to output a calibrated probability over lettered options. It accepts an image and a text question, or text only, and returns a single answer slot. The model is not a chat or captioner model.
Good at
- Single‑slot multiple‑choice image tasks
- Fast inference with small VRAM
- Calibrated probability outputs
Limits
- No generation or chat capability
- Requires 8k context for full performance
- License is apache‑2.0
Best for
- Image‑based quiz answering
- Game‑play decision making from pixels
- Rapid inference on edge devices
Who it’s for. Developers building vision‑language decision systems that need a single‑slot answer. Researchers testing calibrated probability outputs on image‑question pairs. Teams deploying lightweight models on limited GPU memory.
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 (file size 1.27 GB, estimated 2.2 GB memory). For 4 GB VRAM, Q3_K_M (1.1 GB, 2 GB memory). If memory is not a constraint, F16 (3.78 GB, 4.7 GB memory) gives the highest quality.
What GPU do you need for Decider 2b Vision?
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 Decider 2b Vision quant should you choose?
Q4_K_M is the usual starting point for Decider 2b Vision: 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 Decider 2b Vision
How much VRAM does Decider 2b Vision 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 Decider 2b Vision 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 Decider 2b Vision 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 Decider 2b Vision 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 Decider 2b Vision GGUF?
The files are on Hugging Face in the mradermacher/decider-2b-vision-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 Decider 2b Vision 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 Decider 2b Vision on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.2 GB memory at 8k context, fitting comfortably on 8 GB VRAM.
Does the model support text‑only questions?
Yes, it behaves like decider‑2b v5 for text‑only inputs, providing calibrated letter probabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.