# Alibi Serikbay: jevk5

> Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.

- Page: https://systemonemodels.ai/alibi-serikbay/jevk5
- API: https://api.systemonemodels.ai/v1/models/alibi-serikbay/jevk5
- Download: `pip install systemonemodels && systemone pull alibi-serikbay/jevk5`

## Facts

| | |
|---|---|
| Maker | Alibi Serikbay (https://systemonemodels.ai/alibi-serikbay) |
| Decides | choice, score, noul, classify, route |
| Architecture | jevk5 |
| Base model | qwen/qwen3.5-4b |
| Parameters | 4.0B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-22 |
| Latest version | 0.3.0 |

## Reported evaluation

Suite: JevBench public hard tier. Numbers are the publisher's own.

- Decision accuracy: 78.4%
- Calibration error (ECE): 0.035
- Median latency: 13.2 ms

## Model card

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

# JevK5

Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.

Version 0.3 scores 78.4% on JevBench's public hard tier (standard 94.4%, easy 100%) with a calibration error of 0.035 on held-out teacher questions; JevBench v1.4 ranked the previous version second of 76 entries. The Hub lists it as text generation, but decisions come from the jevk5 runtime's readout, and jevk5-serve exposes /v1/systemone. Teacher data was generated under OpenAI's terms. Median latency is 13.2 ms on an H100 for short inputs. Siblings: JevK5-9B, JevK5-2B and JevK5-GGUF.

## 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
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 4B |
| Base model | `qwen/qwen3.5-4b` |
| Maker | Alibi Serikbay |
| Released | 2026-09-22 |
| License | apache-2.0 |
| Reported accuracy | 78.4% |
| Reported latency | 13.2 ms p50 / 14.6 ms p95 on H100 (short); ~30 ms p50 with 1–4k-token documents |

## Get the weights

```bash
pip install systemonemodels
systemone pull alibi-serikbay/jevk5
```

The files are served from the maker's Hugging Face repository, [`alibiserikbay/JevK5`](https://huggingface.co/alibiserikbay/JevK5), and verified against the checksums recorded here.

## Read more

- [Source](https://github.com/allebee/jevk5)
- [Weights on Hugging Face](https://huggingface.co/alibiserikbay/JevK5)

---

*This page was opened by System One for Alibi Serikbay, 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