UniMate-Weights is an open-weight model for text to 3d from Tarn59, released under MIT License. It has 74M parameters. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 83 downloads a month.
A from-scratch training run of the main UniMate model ("UniMate: One Unified Model to Animate Diverse Skeletons", Mou et al., SIGGRAPH Asia 2026, arXiv 2609.05415) on a single GPU, using the authors' released code and the shipped…
Runs On
What it takes to serve UniMate-Weights (74M 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 | 0.1 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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 Sep 24, 2026.
UniMate-Weights on every accelerator the SAVRN Index prices, at every precision
Model Card
By Tarn59, published under mit, revision 518325e09a55.
UniMate uniml3d_60frames_graph_adaln — independently trained checkpoint (v2)
A from-scratch training run of the main UniMate model
("UniMate: One Unified Model to Animate Diverse Skeletons", Mou et al., SIGGRAPH Asia 2026,
arXiv 2609.05415) on a single GPU, using the authors' released
code and the shipped configs/uniml3d_60frames_graph_adaln.json config unchanged.
This repository holds two runs. The files at the root are v2, trained on an audited copy of
the dataset from which 13 defective clips were removed and 18 repaired (see Why v2).
The earlier v1 run on the unaudited data is kept under v1/ for comparison. Use v2.
Identity and Version
- Repository
- tarn59/UniMate-Weights
- Publisher
- Tarn59
- Task
- Text to 3d
- Modality
- Other
- Library
- pytorch
- Parameters
- 74M parameters
- Languages
- Not stated by the source
- Revision
- 518325e09a555f059ba0efe6face299e9b853d8c
- First published
- 2026-09-19
- Last updated
- 2026-09-24
Files and Weights
39 files, 3.6 GB in total. The weights are 6 files totalling 3.6 GB in pt, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoints/checkpoint_step_120000.pt | Weights | 1.2 GB | ee58a7c08b59 |
| model.safetensors | Weights | 296.4 MB | c871afe2991a |
| model_ema.safetensors | Weights | 296.4 MB | 716b8b359216 |
| v1/checkpoints/checkpoint_step_120000.pt | Weights | 1.2 GB | 116fbc42f243 |
| v1/model.safetensors | Weights | 296.4 MB | d0a96d7355eb |
| v1/model_ema.safetensors | Weights | 296.4 MB | ac7027bde593 |
| audit/patch_log.json | Configuration | 3.9 KB | — |
| audit/patch_poison.py | Configuration | 5.3 KB | — |
| audit/poison_tiers.json | Configuration | 12.9 KB | — |
| audit/score_clips.py | Configuration | 6.7 KB | — |
| config.json | Configuration | 3.2 KB | — |
| train_config_as_launched.json | Configuration | 2.3 KB | — |
| v1/config.json | Configuration | 3.2 KB | — |
| v1/train_config_as_launched.json | Configuration | 2.3 KB | — |
| LICENSE | Documentation | 1.1 KB | — |
| README.md | Documentation | 14.1 KB | — |
| audit/POISON_REPORT.md | Documentation | 10.6 KB | — |
| v1/README.md | Documentation | 628 B | — |
| audit/applied_skip_list_objaverse.txt | Other | 1.5 KB | — |
| audit/clip_losses.csv | Other | 2.3 MB | — |
| audit/filtered_clips_objaverse.txt | Other | 3.5 KB | — |
| audit/filtered_clips_truebones.txt | Other | 426 B | — |
| audit/gacha07_preview.png | Other | 156.5 KB | 5c566cf19735 |
| audit/santa_running_preview.png | Other | 129.6 KB | 83b751af5bd0 |
| dataset_stats.npy | Other | 1.9 KB | 653a9c7c2ec7 |
| examples/mixamo_leaps_up_and_hangs.mp4 | Other | 99.6 KB | — |
| examples/objaverse_669a7e6e_scuttles_sideways.mp4 | Other | 84.9 KB | — |
| examples/objaverse_7f020c8e_dances_in_place.mp4 | Other | 103.1 KB | ae1930f2e316 |
| examples/truebones_eagle_sits_spreads_wings.mp4 | Other | 95.2 KB | — |
| logs/events.out.tfevents.1790095024.stuporComputer.510986.0 | Other | 921.8 KB | 350e93d2374f |
| training_curves.png | Other | 219.2 KB | 6e49164fa566 |
| v1/dataset_stats.npy | Other | 1.9 KB | d24f7f601329 |
| v1/examples/mixamo_jumps_while_running_arm_extended.mp4 | Other | 95.8 KB | — |
| v1/examples/objaverse_669a73d2_sways_hips_and_legs.mp4 | Other | 97.9 KB | — |
| v1/examples/objaverse_eeb9bae9_backflip.mp4 | Other | 119.0 KB | abbea91a8a32 |
| v1/examples/truebones_crocodile_bounces_then_collapses.mp4 | Other | 98.3 KB | — |
| v1/logs/events.out.tfevents.1789699593.stuporComputer.464765.0 | Other | 921.8 KB | c3aba82b795e |
| v1/training_curves.png | Other | 221.5 KB | b757bc34c3b6 |
| .gitattributes | Repository | 1.9 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 3.6 GB
Released by Tarn59 through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2609.05415
- Trained on (disclosed) Linzhan/UniML3D
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.6 GB |
| 16-bit | 0.1 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About UniMate-Weights
How much GPU memory does UniMate-Weights need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (74M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run UniMate-Weights 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 UniMate-Weights commercially?
Yes. UniMate-Weights is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.