MoSE3 is an open-weight model from Joanna Cheng, released under Creative Commons Attribution-NonCommercial 4.0. It has 1.5B parameters. At 16-bit it needs about 3.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
MoSE3 is a feed-forward model that predicts world-space SE(3) motion for every pixel of a monocular RGB video, generalizing across rigid, articulated and deformable objects. The code repository has the full inference and visualization scripts.
Runs On
What it takes to serve MoSE3 (1.5B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 3.1 GB | 3.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.5 GB | 1.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
MoSE3 on every accelerator the SAVRN Index prices, at every precision
Model Card
MoSE3 is a feed-forward model that predicts world-space SE(3) motion for every pixel of a monocular RGB video, generalizing across rigid, articulated and deformable objects. The code repository has the full inference and visualization scripts. The weights are released under CC BY-NC 4.0 (non-commercial). They include the weights of π³, which are released under the same license.
Excerpt from the card by Joanna Cheng, licensed cc-by-nc-4.0.
Identity and Version
- Repository
- JoannaCCCCCC/MoSE3
- Publisher
- Joanna Cheng
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 1.5B parameters
- Languages
- Not stated by the source
- Revision
- a7b47127a144c1659220b0cb2d00f5aceeb53c3c
- First published
- 2026-09-27
- Last updated
- 2026-10-05
Files and Weights
4 files, 6.2 GB in total. The weights are 1 file totalling 6.2 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 6.2 GB | fcbd51ff01c2 |
| config.json | Configuration | 331 B | — |
| README.md | Documentation | 1.3 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 6.2 GB
Released by Joanna Cheng through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2610.03716
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.2 GB |
| 16-bit | 3.1 GB |
| 8-bit | 1.5 GB |
| 4-bit | 0.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About MoSE3
How much GPU memory does MoSE3 need?
About 3.7 GB at 16-bit and 0.9 GB at 4-bit: the weights (1.5B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run MoSE3 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use MoSE3 commercially?
Not without separate permission. MoSE3 is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.