SkinTokens GGUF BF16 needs about 0.8 GB of memory at its main file (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB to 0.9 GB.
SkinTokens GGUF BF16 – lightweight rigging model
SkinTokens GGUF BF16 is a 28.8 M‑parameter model for generating skeletons and skinning weights from 3D meshes. It is a GGUF conversion of the original SkinTokens checkpoints, keeping BF16 matrices. The model is released under the MIT license.
Good at
- Unified skeleton and skinning generation
- Compact 28.8 M parameters
- BF16 precision for efficient inference
Limits
- No vision support
- Requires both TokenRig and FSQ‑CVAE checkpoints for full inference
- Context length not specified
Best for
- Procedural character rigging
- Game asset pipeline automation
- Rapid prototyping of 3D models
Who it’s for. Developers and researchers needing an end‑to‑end rigging solution that combines skeleton and skinning generation. The model is suitable for projects that can integrate the required checkpoints and run on GPU hardware with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| — | 0.9 GB | 1.6 GB | Fits | Get file → |
The three GGUF files are 0.06 GB, 0.24 GB, and 0.95 GB. Memory usage at 8 k context is approximately 0.6 GB, 0.8 GB, and 1.6 GB respectively. Choose the smallest file for 8 GB VRAM or the 0.95 GB file for higher fidelity if memory allows.
What GPU do you need for SkinTokens GGUF BF16?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 1.6 GB in use).
Which SkinTokens GGUF BF16 quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SkinTokens GGUF BF16
How much VRAM does SkinTokens GGUF BF16 need?
About 0.8 GB at its main file with an 8K context window. That is the 0.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run SkinTokens GGUF BF16 on an 8 GB GPU?
Yes, with the smaller files: the 0.9 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SkinTokens GGUF BF16 GGUF?
It depends on the quant: file is 0.1 GB, file is 0.2 GB, file is 0.9 GB.
Where can I download SkinTokens GGUF BF16 GGUF?
The files are on Hugging Face in the chibifire/SkinTokens-GGUF-BF16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SkinTokens GGUF BF16 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run SkinTokens GGUF BF16 on 8 GB VRAM?
Yes, the 0.06 GB file uses about 0.6 GB at 8 k context, well within 8 GB VRAM limits.
Do I need additional checkpoints for inference?
Yes, both the TokenRig and FSQ‑CVAE checkpoints are required for full end‑to‑end rigging.