# ORG2 AI: wald

> A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.

- Page: https://systemonemodels.ai/org2ai/wald
- API: https://api.systemonemodels.ai/v1/models/org2ai/wald
- Download: `pip install systemonemodels && systemone pull org2ai/wald`

## Facts

| | |
|---|---|
| Maker | ORG2 AI (https://systemonemodels.ai/org2ai) |
| Decides | choice, score, noul, classify, route |
| Architecture | wald |
| Base model | qwen/qwen3.5-4b-base |
| Parameters | 4.2B |
| Context | 128K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-01 |
| Latest version | 1.2.0 |

## Reported evaluation

Suite: JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard. Numbers are the publisher's own.

- Decision accuracy: 88.3%
- Calibration error (ECE): 0.045
- Median latency: 33 ms
- p95 latency: 168 ms

## Model card

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

# Wald-Q4B (Wald-4B v1.2)

A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.

v1.2 (main since 1 October) is v1.1 plus a merged rank-16 robustness LoRA and is one-pass only. v1.1 (tag v1.1) has optional thinking efforts that generate up to 512 tokens before reading the options again; pin a revision. The shipped server needs one NVIDIA GPU with vLLM; the maker's GGUF builds run through its own wald-serve on llama.cpp, while chat front-ends return text, not probabilities. All numbers are self-run: the public JevBench items (a third-party benchmark) were used as a development scoreboard, so 204/231 is not held out; the maker's own Decision Index 0.2.1 run (54.59, v1.1 with high effort) awaits validation by that third-party board. Calibration was fitted on the maker's development data. Some training text was written by Claude Haiku, and the maker's provenance notes say part of the training data has non-commercial terms. Independent of TypeSafe; the server adapts Kev and simple-jev code under Apache-2.0. First published as Harry19081/Wald-4B.

## 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
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 4.2B |
| Base model | `Qwen/Qwen3.5-4B-Base` |
| Maker | ORG2 AI |
| Released | 2026-10-01 |
| License | apache-2.0 |
| Reported accuracy | 88.3% |
| Reported latency | 33 ms p50 / 168 ms p95 per decision on one RTX PRO 6000, effort none (measured on v1.1) |

## Get the weights

```bash
pip install systemonemodels
systemone pull org2ai/wald
```

The files are served from the maker's Hugging Face repository, [`org2ai/Wald-4B`](https://huggingface.co/org2ai/Wald-4B), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/org2ai/Wald-4B)
- [Code and server](https://github.com/org2AI/wald-4b)
- [GGUF builds](https://huggingface.co/org2ai/Wald-4B-GGUF)

---

*This page was opened by System One for ORG2 AI, 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