# LibertAI: deem

> LibertAI's open-weights decision model on Qwen3.5-9B-Base. It reads a state and returns a typed choice, ordinal score or yes/no with abstention, read from a letter slot in one prefill pass with a probability per option. CPU-native 0.8B and 0.6B siblings.

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

## Facts

| | |
|---|---|
| Maker | LibertAI (https://systemonemodels.ai/libertai) |
| Decides | choice, score, noul |
| Architecture | deem |
| Base model | qwen/qwen3.5-9b-base |
| Parameters | 9.0B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-24 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: JevBench public hard tier (111 items), LibertAI's own run of the 9B, single pass. Numbers are the publisher's own.

- Decision accuracy: 65.8%

## Model card

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

# Deem 9B (v1)

LibertAI's open-weights decision model on Qwen3.5-9B-Base. It reads a state and returns a typed choice, ordinal score or yes/no with abstention, read from a letter slot in one prefill pass with a probability per option. CPU-native 0.8B and 0.6B siblings.

A LoRA-merged fine-tune with a letter-slot readout; the served response shows zero output tokens. Siblings LibertAIDAI/deem-0.8-v1 (Qwen3.5-0.8B; root weights are v1.1, with v1.0 kept in a subfolder) and LibertAIDAI/deem-0.6-v1 (Qwen3-0.6B-Base) run on LibertAI's own Rust CPU runtime with AVX-512 bf16 and int8 kernels; the maker reports 96.2% on its long-policy hold-out for the 0.8B, at 362 ms per short decision on a busy desktop CPU. On the third-party JevBench public set the maker reports, for the 9B, 100.0 easy, 91.7 original and 65.8 hard (68.9 with its optional extended-reasoning mode, which generates text before answering and is not one pass). LibertAI's servers cap choice questions at 26 options although the card says 2 to 255. Temperatures are shipped but no calibration figure is published. The maker says it never trained on JevBench. No hosted API. Not related to mertkayacs/Deem-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

## At a glance

| | |
|---|---|
| Parameters | 9B |
| Base model | `Qwen/Qwen3.5-9B-Base` |
| Maker | LibertAI |
| Released | 2026-09-24 |
| License | apache-2.0 |
| Reported accuracy | 65.8% |
| Reported latency | about 100 ms p50 per short decision on a low-power edge GPU (model not named); 788 ms p50 for policies of 3,200+ tokens |

## Get the weights

```bash
pip install systemonemodels
systemone pull libertai/deem
```

The files are served from the maker's Hugging Face repository, [`LibertAIDAI/deem-9b-v1`](https://huggingface.co/LibertAIDAI/deem-9b-v1), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/LibertAIDAI/deem-9b-v1)
- [Deem 0.8B (CPU)](https://huggingface.co/LibertAIDAI/deem-0.8-v1)
- [Deem 0.6B (CPU)](https://huggingface.co/LibertAIDAI/deem-0.6-v1)
- [Code, servers and Tare harness](https://github.com/Libertai/deem)

---

*This page was opened by System One for LibertAI, 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