Jev-Style-2B-Decision-v3 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 3 quants, from 1.3 GB (Q4_K_M) to 3.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Jev-Style-2B-Decision-v3: 2B‑parameter decision‑only model
Jev-Style-2B-Decision-v3 is a 1.9B‑parameter Qwen3.5‑based model that scores options and returns probabilities. It is optimized for decision tasks and does not generate text. The model is available as a free hosted API and as GGUF files for local use.
Good at
- Option scoring with calibrated probabilities
- Fast inference on short requests
- No text generation, pure decision logic
Limits
- No vision or text generation
- Input capped at 8,000 tokens on free API
- Requires bundled scorer for local use
Best for
- Decision‑making workflows
- Automated QA scoring
- Batch option evaluation
Who it’s for. Developers building decision‑making services or QA pipelines that need reliable probability scores for multiple options. The model is suitable for applications that require quick, deterministic scoring without text output.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.3 GB | 2.2 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 VRAM at 8 k context). For 12 GB VRAM, Q8_0 (2.01 GB, ~2.9 GB VRAM). For 16 GB VRAM or more, F16 (3.78 GB, ~4.7 GB VRAM). Estimates are approximate.
What GPU do you need for Jev-Style-2B-Decision-v3?
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-Style-2B-Decision-v3 quant should you choose?
Q4_K_M is the usual starting point for Jev-Style-2B-Decision-v3: 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jev-Style-2B-Decision-v3
How much VRAM does Jev-Style-2B-Decision-v3 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-Style-2B-Decision-v3 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-Style-2B-Decision-v3 GGUF?
It depends on the quant: Q4_K_M is 1.3 GB, Q8_0 is 2.0 GB, F16 is 3.8 GB.
What context length does Jev-Style-2B-Decision-v3 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 Jev-Style-2B-Decision-v3 GGUF?
The files are on Hugging Face in the chaoliangUNSW/Jev-Style-2B-Decision-v3-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-Style-2B-Decision-v3 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 Jev-Style-2B-Decision-v3 on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 2.2 GB VRAM at 8 k context, which fits within 8 GB.
Does the model support text generation?
No, it only scores options and returns probabilities; it does not generate text.
What is the maximum context length?
The model supports up to 25,600 tokens for state, questions, and options combined.