# Mapika: decider

> A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.

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

## Facts

| | |
|---|---|
| Maker | Mapika (https://systemonemodels.ai/mapika) |
| Decides | choice, score, noul, classify, route |
| Architecture | decider |
| Base model | qwen/qwen3.5-2b-base |
| Parameters | 1.9B |
| Context | 32K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-24 |
| Latest version | v11 |

## Reported evaluation

Suite: Decider regression set, 28 held-out tasks (decider-2b v11). Numbers are the publisher's own.

- Decision accuracy: 75.2%

## Fine-tunes on the registry

- flock-io/this-that-model: https://systemonemodels.ai/flock-io/this-that-model

## Model card

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

# Decider family

A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.

Unofficial listing, compiled from Mark Marosi's public releases; the source is the GitHub repository and the Hugging Face repositories linked below. The files here are decider-2b v11 (Qwen3.5-2B-Base, 1.9B parameters, 32k context), released on 24 September 2026 with decider-4b v2.1; the family's first release was on 16 September. The family: decider-0.8b (Qwen3.5-0.8B-Base), decider-2b v11, decider-4b v2.1 (Qwen3.5-4B-Base, 4.2B), decider-35b-a3b v1 (Qwen3.5-35B-A3B-Base, 34.7B total and 3B active, also in NVFP4), decider-2b-vision, and GGUF builds of the 2B and 4B, all Apache-2.0 and all serving POST /v1/systemone. On the author's regression set of 28 held-out tasks: decider-2b v11 75.2%, decider-4b v2.1 78.4%, decider-35b-a3b 81.0%. On the JevBench public hard tier: 57.7%, 64.9% and 67.6%. The author's Q8_0 GGUF build gave the same answer as the bf16 weights on 99.16% of 144,000 questions in the author's tests; the playground runs it on a CPU.

## 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 | 1.9B |
| Base model | `qwen/qwen3.5-2b-base` |
| Maker | Mapika |
| Released | 2026-09-24 |
| License | apache-2.0 |
| Reported accuracy | 75.2% |

## Get the weights

```bash
pip install systemonemodels
systemone pull mapika/decider
```

The files are served from the maker's Hugging Face repository, [`Mapika/decider-2b`](https://huggingface.co/Mapika/decider-2b), and verified against the checksums recorded here.

## Read more

- [Source on GitHub](https://github.com/Mapika/decider)
- [decider-0.8b](https://huggingface.co/Mapika/decider-0.8b)
- [decider-2b (v11)](https://huggingface.co/Mapika/decider-2b)
- [decider-4b (v2.1)](https://huggingface.co/Mapika/decider-4b)
- [decider-35b-a3b](https://huggingface.co/Mapika/decider-35b-a3b)
- [decider-35b-a3b-nvfp4](https://huggingface.co/Mapika/decider-35b-a3b-nvfp4)
- [decider-2b-vision](https://huggingface.co/Mapika/decider-2b-vision)
- [decider-2b-GGUF](https://huggingface.co/Mapika/decider-2b-GGUF)
- [decider-4b-GGUF](https://huggingface.co/Mapika/decider-4b-GGUF)

---

*This page was opened by System One for Mapika, 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