Model reference · open weights
ConsiSpace is an open-weight language model from BAAI. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | BAAI |
|---|---|
| Type | Language models |
| Task | Vision + text |
| Parameters (lead) | 5.7B |
| Context | 125k tokens |
| Runs with | transformers |
| Based on | Qwen/Qwen3-VL-8B-Instruct |
| Released | 2026-09-04 |
| Popularity | 0 downloads / month |
| Licence | Open weights |
About
Official model weights for ConsiSpace.
ConsiSpace is a geometry-consistent multimodal framework for spatial reasoning in long-form visual observations.
📄 Paper: https://arxiv.org/abs/2607.17599
@article{huang2026consispace,
title={ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning},
author={Ting Huang and Zhenyu Zhang and Wenyuan Huang and Jian Yang and Hao Tang},
year={2026},
eprint={2607.17599},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2607.17599},
}
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys consispace for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (consispace below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"consispace","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.