# Yun Qu: mentat-sys1

> A LoRA adapter and native decision readout on Qwen3.5-4B that answers noul, choice and score questions in one forward pass, with a probability per supplied label and a frozen scalar temperature. Self-hosted, it serves the TypeSafe /v1/systemone wire format.

- Page: https://systemonemodels.ai/yun-qu/mentat-sys1
- API: https://api.systemonemodels.ai/v1/models/yun-qu/mentat-sys1
- Download: `pip install systemonemodels && systemone pull yun-qu/mentat-sys1`

## Facts

| | |
|---|---|
| Maker | Yun Qu (https://systemonemodels.ai/yun-qu) |
| Decides | choice, score, noul |
| Architecture | mentat |
| Base model | qwen/qwen3.5-4b |
| Parameters | 4.0B |
| Context | 16K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-04 |
| Latest version | 0.1.0 |

## Reported evaluation

Suite: JevBench public set (231 items, rev 2fa63fa), maker's run, two identical runs. Numbers are the publisher's own.

- Decision accuracy: 86.6%
- Calibration error (ECE): 0.058

## Model card

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

# mentat-sys1-v0.1

A LoRA adapter and native decision readout on Qwen3.5-4B that answers noul, choice and score questions in one forward pass, with a probability per supplied label and a frozen scalar temperature. Self-hosted, it serves the TypeSafe /v1/systemone wire format.

A personal release by Yun Qu, with weights on Hugging Face and serving code in the mentat-asi GitHub organisation. The repo holds the adapter (rank 64, about 488 MB) and the readout, not the base weights. The temperature was fitted on a separate 1,120-row reserve set; responses add unknown-probability and abstained fields. The serving code is adapted from the Apache-2.0 Imajev project; the weights are stated to be trained independently. By the maker's own statement the training-data source and licence ledger is incomplete. The numbers are the maker's run on JevBench's public items (a third-party board), which the maker calls local measurements, not leaderboard claims; JevBench has not run it yet. No hosted API.

## 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

## At a glance

| | |
|---|---|
| Parameters | 4B |
| Base model | `Qwen/Qwen3.5-4B` |
| Maker | Yun Qu |
| Released | 2026-10-04 |
| License | apache-2.0 |
| Reported accuracy | 86.6% |
| Reported latency | 90 to 91 ms p50 / 332 to 336 ms p95 serial on one A800 80GB |

## Get the weights

```bash
pip install systemonemodels
systemone pull yun-qu/mentat-sys1
```

The files are served from the maker's Hugging Face repository, [`yunqu/mentat-sys1-v0.1`](https://huggingface.co/yunqu/mentat-sys1-v0.1), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/yunqu/mentat-sys1-v0.1)
- [Serving code](https://github.com/mentat-asi/mentat-sys1-v0.1)

---

*This page was opened by System One for Yun Qu, 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