decider-2b-v10 needs about 2.9 GB of memory at Q8_0 (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.2 GB (IQ4_NL) to 3.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Decider-2B v10: a Qwen3.5-2B-Base fine‑tune that returns option probabilities without text generation
Decider-2B v10 is a 1.88B parameter model based on Qwen3.5-2B-Base. It reads a state and typed questions with explicit option lists and outputs a probability distribution over the options in a single forward pass. The model supports text and image inputs via the decider‑ai server.
Good at
- Option probability inference
- Reasoning with explicit choices
- Tool‑aware decision making
Limits
- No text generation
- Limited context to 262144 tokens
- Requires Apache‑2.0 license
Best for
- Automated decision engines
- Question‑answering systems with predefined options
- Tool‑integrated workflows
Who it’s for. Developers building decision‑making services that need calibrated probabilities for each option. The model is ideal for applications that call an API to receive a probability distribution rather than a text response.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 1.2 GB | 2.1 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, the IQ4_NL quant (~1.24 GB) uses about 2.1 GB memory at 8 k context, which is safe. If more VRAM is available, Q8_0 (~2.01 GB) uses about 2.9 GB memory. The F16 quant (~3.78 GB) requires about 4.7 GB memory and is best for high‑precision inference on larger GPUs.
What GPU do you need for decider-2b-v10?
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-v10 quant should you choose?
Q8_0 (2.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is IQ4_NL at 1.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about decider-2b-v10
How much VRAM does decider-2b-v10 need?
About 2.9 GB at Q8_0 with an 8K context window. That is the 2.0 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-v10 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-v10 GGUF?
It depends on the quant: IQ4_NL is 1.2 GB, Q8_0 is 2.0 GB, F16 is 3.8 GB.
What context length does decider-2b-v10 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-v10 GGUF?
The files are on Hugging Face in the cosetoenor/decider-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 decider-2b-v10 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 v10 on 8 GB VRAM?
Yes, the IQ4_NL quant uses about 2.1 GB memory at 8 k context, well within an 8 GB VRAM budget.
Does Decider-2B support image inputs?
Yes, the model includes a vision tower and can process up to 4 images per request via the decider‑ai server.