# Jared Palmer: kev

> An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.

- Page: https://systemonemodels.ai/jared-palmer/kev
- API: https://api.systemonemodels.ai/v1/models/jared-palmer/kev
- Download: `pip install systemonemodels && systemone pull jared-palmer/kev`

## Facts

| | |
|---|---|
| Maker | Jared Palmer (https://systemonemodels.ai/jared-palmer) |
| Decides | choice, score, noul, classify, route |
| Architecture | kev |
| Base model | qwen/qwen3.5-4b-base |
| Parameters | 4.0B |
| Context | 8K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-19 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: transfer-v4 (locked, out of domain). Numbers are the publisher's own.

- Decision accuracy: 83.8%
- Calibration error (ECE): 0.042

## Model card

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

# Kev

An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.

This entry is kev-4b on Qwen3.5-4B-Base, the family's reference size; the adapter is rank 16 (33.8M parameters) and the repository holds the adapter and head, not the base weights. On the locked out-of-domain test (transfer-v4) as served it scores 83.8% with an expected calibration error of 0.042; in-distribution 87.3%. Siblings, all Apache-2.0: kev-0.8b (69.7% out of domain), kev-9b (85.2%, Brier 0.237), kev-27b on Qwen's post-trained Qwen3.8-27B (89.6% on the same test, the most accurate Kev; 84.8% on development sources, where Jev scores 85.7%), and kev-8b, kev-0.6b and kev-0.5b on older bases. Serving context is 8,192 tokens; Choice and Score take up to 255 options. No Jev outputs were used in training. Model time is 36–179 ms on an L40S; Apple silicon is slow (DeltaNet kernels).

## 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-base` |
| Maker | Jared Palmer |
| Released | 2026-09-19 |
| License | apache-2.0 |
| Reported accuracy | 83.8% |
| Reported latency | 36–179 ms model time on L40S; ~495 ms per sample on Apple M5 |

## Get the weights

```bash
pip install systemonemodels
systemone pull jared-palmer/kev
```

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

## Read more

- [Source and API](https://github.com/jaredpalmer/kev)
- [kev-4b on Hugging Face](https://huggingface.co/jaredpalmer/kev-4b)
- [kev-0.8b](https://huggingface.co/jaredpalmer/kev-0.8b)
- [kev-9b](https://huggingface.co/jaredpalmer/kev-9b)
- [kev-27b](https://huggingface.co/jaredpalmer/kev-27b)

---

*This page was opened by System One for Jared Palmer, 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