# Nace.AI: drex-dlm

> Nace.AI's decision model on NVIDIA's Efficient-DLM-8B diffusion backbone: the state is read bidirectionally, each question branch causally, and a pointer head returns a probability for every option in one forward pass. Also sold as the hosted Drex API.

- Page: https://systemonemodels.ai/nace-ai/drex-dlm
- API: https://api.systemonemodels.ai/v1/models/nace-ai/drex-dlm
- Download: `pip install systemonemodels && systemone pull nace-ai/drex-dlm`

## Facts

| | |
|---|---|
| Maker | Nace.AI (https://systemonemodels.ai/nace-ai) |
| Decides | choice, score, noul |
| Architecture | drex |
| Base model | nvidia/efficient-dlm-8b |
| Parameters | 8.2B |
| Context | 32K tokens |
| Licence | cc-by-nc-4.0 |
| Availability | Open weights + hosted API |
| Released | 2026-10-01 |
| Latest version | 2026.09 |

## Hosted API

- Provider: Nace.AI (https://drex.nace.ai)
- Docs: https://drex.nace.ai/docs
- Input: $0.050/MTok · Output: Free

## Model card

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

# Drex DLM

Nace.AI's decision model on NVIDIA's Efficient-DLM-8B diffusion backbone: the state is read bidirectionally, each question branch causally, and a pointer head returns a probability for every option in one forward pass. Also sold as the hosted Drex API.

Nace merged a trained decision adapter into Efficient-DLM-8B and added a pointer head; question branches cannot see each other. The weights take 32,768 tokens; the local runners default to 16,384. It runs through a Python server and Nace's own llama.cpp and Ollama forks; a Q8_0 GGUF sits in a sibling repo. Only tested on Apple Silicon, and long-context quality is experimental; the repo's own 6 October cross-runner check is marked not signed off. The card says choice and score confidence is not a calibrated probability of correctness. Nace quotes 52.31 on the third-party Decision Index 0.2 from its own run; Drex was not on the public board as of 6 October. Weights are CC BY-NC 4.0 from the NVIDIA base, so no commercial rights and no mirroring; code is MIT. The hosted Drex API (drex-v1.0 from 24 September, v1.5 from 28 September) is paid per input token, and Nace does not say which hosted version the open weights match.

## 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 | 8.2B |
| Base model | `nvidia/Efficient-DLM-8B` |
| Maker | Nace.AI |
| Released | 2026-10-01 |
| License | cc-by-nc-4.0 |

## Hosted API

Served by **Nace.AI** — $0.05/MTok input, $0/MTok output. [Get access](https://drex.nace.ai) · [API docs](https://drex.nace.ai/docs).

## Get the weights

```bash
pip install systemonemodels
systemone pull nace-ai/drex-dlm
```

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

## Read more

- [Model card](https://huggingface.co/nace-ai/drex-dlm)
- [Drex API docs](https://drex.nace.ai/docs)

---

*This page was opened by System One for Nace.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