# Intern-Decision model sizes and sources

> Intern-Decision is InternLM's multimodal decision family in 0.8B, 2B and 4B sizes. It returns answer distributions in one pass for text and images.

Updated 2026-11-04 (Australia/Adelaide)

By InternLM · First Hugging Face upload: 2026-09-26 · OPEN

Send a shared state, named questions and optional images to these multimodal models. A single forward pass returns an answer distribution for every question, without generating text. The Qwen3.5-based family has 0.8B, 2B and 4B sizes.

## Facts

- Sizes: 0.8B, 2B and 4B
- Base: Qwen3.5; the 4B model uses Qwen3.5-4B
- Licence: Apache-2.0
- Inputs: Text and images

## Claims and sources

- **VENDOR-REPORTED**: InternLM reports a seven-benchmark average of 90.02 for [Intern-Decision-4B](<https://decisionmodels.ai/models/intern-decision>) against 88.74 for [Jev](<https://decisionmodels.ai/models/jev>), with Brier / ECE of 0.347 / 0.065 against 0.358 / 0.095. [source](<https://huggingface.co/internlm/Intern-Decision-4B>)
- **VENDOR-REPORTED**: The model card reports mean latency of 44.16 ms for the 4B on one RTX 4090, against 109.70 ms for [Jev](<https://decisionmodels.ai/models/jev>). The local and network paths differ, so these timings are not like for like and depend on hardware and workload. [source](<https://huggingface.co/internlm/Intern-Decision-4B>)

## Links

- [Source: 4B weights and model card](<https://huggingface.co/internlm/Intern-Decision-4B>)
- [Source: GitHub](<https://github.com/internlm/Intern-Decision>)
- [Source: Report](<https://arxiv.org/abs/2610.22131>)
- [Source: Hugging Face upload metadata](<https://huggingface.co/api/models/internlm/Intern-Decision-4B>)

## Related projects

No related projects are listed in the registry.