# BRICKS: jevling

> A small System One model on Gemma 4 E2B: a text state and several typed questions (choice, yes/no, score) go in, and one forward pass returns a probability per option, with no generated text. Tuned for on-device kiosk ordering in Traditional Chinese. Apache-2.0.

- Page: https://systemonemodels.ai/bricks/jevling
- API: https://api.systemonemodels.ai/v1/models/bricks/jevling
- Download: `pip install systemonemodels && systemone pull bricks/jevling`

## Facts

| | |
|---|---|
| Maker | BRICKS (https://systemonemodels.ai/bricks) |
| Decides | choice, score, noul, classify |
| Architecture | jevling |
| Base model | google/gemma-4-e2b-it |
| Parameters | 5.1B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-03 |
| Latest version | 2026.09 |

## Model card

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

# Jevling-E2B-v1

A small System One model on Gemma 4 E2B: a text state and several typed questions (choice, yes/no, score) go in, and one forward pass returns a probability per option, with no generated text. Tuned for on-device kiosk ordering in Traditional Chinese. Apache-2.0.

Jevling reads each answer from a letter slot after the question, so all of a state's questions are answered in one pass; the fine-tune trains only that slot and the base can still chat. Calibration is a temperature (1.10) folded into the final norm, and no calibration error is reported. On JevBench's 231 public items (a third-party board) the maker's own run gives 100% easy, 94.4% original and 43.2% hard; the maker also reports 15 public datasets and a zh-TW kiosk set that is its own synthetic data. The maker says v1 was retrained only on commercially usable data. Sibling Jevling-0.8B-v1 on Qwen3.5-0.8B. Both have Q8_0 GGUF builds that need BRICKS's llama.cpp fork (mybigday/system-one-llama.cpp); the maker warns that stock llama.cpp loads them but answers wrongly without an error.

## 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 probability
- **classify** — assigns a category from a fixed taxonomy

## At a glance

| | |
|---|---|
| Parameters | 5.1B |
| Base model | `google/gemma-4-e2b-it` |
| Maker | BRICKS |
| Released | 2026-10-03 |
| License | apache-2.0 |

## Get the weights

```bash
pip install systemonemodels
systemone pull bricks/jevling
```

The files are served from the maker's Hugging Face repository, [`BricksDisplay/jevling-e2b-v1`](https://huggingface.co/BricksDisplay/jevling-e2b-v1), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/BricksDisplay/jevling-e2b-v1)
- [Jevling-0.8B-v1](https://huggingface.co/BricksDisplay/jevling-0.8b-v1)
- [llama.cpp fork](https://github.com/mybigday/system-one-llama.cpp)

---

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

---

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