SkinTokens-GGUF-BF16 is an open-weight model from Chibifire, released under MIT License. Its published files total 1.3 GB.
GGUF files of VAST-AI/SkinTokens with the checkpoint's BF16 matrices kept in BF16. 1-D and sensitive tensors are F32. The files are a format change of the released model. Nobody trained them again.
Model Card
By Chibifire, published under mit, revision 912d4d15c771.
GGUF files of VAST-AI/SkinTokens with the checkpoint's BF16 matrices kept in BF16. 1-D and sensitive tensors are F32. The files are a format change of the released model. Nobody trained them again. The converter is scripts/converttogguf.py --ftype 2 of V-Sekai-fire/skin-tokens-ggml at commit Keep the three files together. SHA256SUMS has their checksums. The SkinTokens auto-rig Space reads these files in the browser and rigs a model on your GPU with WebGPU. The original model card is the reference for intended use, training data and citation.
Read Chibifire's full model card
GGUF files of VAST-AI/SkinTokens with the
checkpoint's BF16 matrices kept in BF16. 1-D and sensitive tensors are F32. The files are a format
change of the released model. Nobody trained them again.
The converter is scripts/convert_to_gguf.py --ftype 2 of
V-Sekai-fire/skin-tokens-ggml at commit
f0c086c28146ff9ea244cd9c7b20af51b4ef04e7.
| File | Part | Size |
|---|---|---|
mesh-encoder.gguf |
Michelangelo point encoder | 57.8 MB |
tokenrig.gguf |
Qwen3-0.6B TokenRig policy | 948.6 MB |
skin-vae.gguf |
SkinTokens condition encoder and decoder | 244.0 MB |
Keep the three files together. SHA256SUMS has their checksums.
The SkinTokens auto-rig Space reads these files in the browser and rigs a model on your GPU with WebGPU.
The original model card is the reference for intended use, training data and citation.
Identity and Version
- Repository
- chibifire/SkinTokens-GGUF-BF16
- Publisher
- Chibifire
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 912d4d15c771a7d99d143802d0a103d8a45fa0c6
- First published
- 2026-10-18
- Last updated
- 2026-10-18
Files and Weights
6 files, 1.3 GB in total. The weights are 3 files totalling 1.3 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| mesh-encoder.gguf | Weights | 57.8 MB | e64519b5b546 |
| skin-vae.gguf | Weights | 244.0 MB | 4cb1917957e4 |
| tokenrig.gguf | Weights | 948.6 MB | f088b53c1429 |
| README.md | Documentation | 1.2 KB | — |
| SHA256SUMS | Other | 244 B | — |
| .gitattributes | Repository | 1.7 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 1.3 GB
Released by Chibifire through its official repository on Hugging Face. Read the license.
Built From
- Derived from VAST-AI/SkinTokens
- Quantized from VAST-AI/SkinTokens
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About SkinTokens-GGUF-BF16
Can I use SkinTokens-GGUF-BF16 commercially?
Yes. SkinTokens-GGUF-BF16 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.