# InternLM (Shanghai AI Laboratory): intern-decision

> Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.

- Page: https://systemonemodels.tech/internlm/intern-decision
- API: https://api.systemonemodels.tech/v1/models/internlm/intern-decision
- Download: `pip install systemonemodels && systemone pull internlm/intern-decision`

## Facts

| | |
|---|---|
| Maker | InternLM (Shanghai AI Laboratory) (https://systemonemodels.tech/internlm) |
| Decides | choice, score, noul, classify, route |
| Architecture | intern-decision |
| Base model | qwen/qwen3.5-4b |
| Parameters | 4.5B |
| Context | 8K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-26 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions). Numbers are the publisher's own.

- Decision accuracy: 80.6%

- Median latency: 44 ms
- p95 latency: 44.6 ms

## Model card

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

# Intern-Decision-4B

Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.

Each question's options become single-token symbols and the answer is read from the logits just before a decision placeholder in a JSON skeleton; nothing is sampled. Choice takes up to 62 options and inputs up to 8,192 tokens (longer ones are rejected, not truncated). InternLM reports 80.6% on the LocalLLaMA/typed-decisions test split, 100 / 98.6 / 73.9% on JevBench's public easy, original and hard tiers (201 of 231), a 90.0% mean over seven suites (its own run of Jev: 88.7%), and ECE 0.065 on the hard tier. Siblings: Intern-Decision-2B (84.7% seven-suite mean) and 0.8B (79.4%). Weights are Apache-2.0 with the Qwen licence notices kept; the training data is not released. The third-party Decision Index 0.2.1 puts the 4B at 37.81.

## 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 | 4.5B |
| Base model | `qwen/qwen3.5-4b` |
| Maker | InternLM (Shanghai AI Laboratory) |
| Released | 2026-09-26 |
| License | apache-2.0 |
| Reported accuracy | 80.6% |
| Reported latency | 44.0 ms p50 / 44.6 ms p95 per three-question request (289 tokens) on one RTX 4090, BF16, Hugging Face path |

## Get the weights

```bash
pip install systemonemodels
systemone pull internlm/intern-decision
```

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

## Read more

- [Model card](https://huggingface.co/internlm/Intern-Decision-4B)
- [Code](https://github.com/internlm/Intern-Decision)
- [Intern-Decision-2B](https://huggingface.co/internlm/Intern-Decision-2B)
- [Intern-Decision-0.8B](https://huggingface.co/internlm/Intern-Decision-0.8B)
- [Demo](https://huggingface.co/spaces/internlm/intern-decision)

---

*This page was opened by System One for InternLM (Shanghai AI Laboratory), who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.tech/ · every System One model: https://systemonemodels.tech/system-one-models