# StartLux: startlux-decision

> StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.

- Page: https://systemonemodels.tech/startlux/startlux-decision
- API: https://api.systemonemodels.tech/v1/models/startlux/startlux-decision
- Download: `pip install systemonemodels && systemone pull startlux/startlux-decision`

## Facts

| | |
|---|---|
| Maker | StartLux (https://systemonemodels.tech/startlux) |
| Decides | choice, score, noul |
| Architecture | startlux-decision |
| Parameters | 4.7B |
| Licence | cc-by-nc-4.0 |
| Availability | Open weights |
| Released | 2026-09-29 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: JevBench public set (231 items; 204 correct), maker's run. Numbers are the publisher's own.

- Decision accuracy: 88.3%

- Median latency: 26 ms

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# StartLux-Decision-4B

StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.

The card does not name a base model; the configuration is a Qwen3.5-architecture checkpoint. The 4B answers 204 of JevBench's 231 public items (as bundled by Intern-Decision) and takes 26.0 ms for a three-question request, 14.7 ms for one yes/no question, end to end on one H200 in BF16. StartLux also quotes a Decision Index 0.2.1 score of 52.75 from its own run; the model was not on the public board as of 28 September. The 27B answers 208 of 231. Weights are CC BY-NC 4.0 (commercial use needs a licence from StartLux, so do not mirror); the inference code is Apache-2.0. GGUF builds exist for every size.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one calibrated probability

## At a glance

| | |
|---|---|
| Parameters | 4.7B |
| Maker | StartLux |
| Released | 2026-09-29 |
| License | cc-by-nc-4.0 |
| Reported accuracy | 88.3% |
| Reported latency | 26.0 ms per three-question request, 14.7 ms per yes/no question, end to end over HTTP on one H200 (BF16) |

## Get the weights

```bash
pip install systemonemodels
systemone pull startlux/startlux-decision
```

The files are served from the maker's Hugging Face repository, [`startlux-models/StartLux-Decision-4B`](https://huggingface.co/startlux-models/StartLux-Decision-4B), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/startlux-models/StartLux-Decision-4B)
- [StartLux-Decision-27B](https://huggingface.co/startlux-models/StartLux-Decision-27B)
- [StartLux-Decision-0.8B](https://huggingface.co/startlux-models/StartLux-Decision-0.8B)

---

*This page was opened by System One for StartLux, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.tech/ · every System One model: https://systemonemodels.tech/system-one-models