face detect needs about 0.6 GB of memory at its main file (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.0 GB to 0.3 GB.
Face detection and recognition model for LocalAI
The face-detect GGUF packs provide a self‑contained face detection, recognition, genderage, and anti‑spoofing pipeline. Each pack is a f16 GGUF file with the full forward graph in metadata, enabling inference without Python or ONNX runtime.
Good at
- Face detection
- Face recognition
- Genderage and anti‑spoofing
Limits
- No vision support beyond face processing
- License varies: non‑commercial or Apache‑2.0
- Model size up to 0.25 GB
Best for
- Embedded face‑analysis applications
- Research prototypes requiring quick inference
- LocalAI face‑detect backend
Who it’s for. Developers building face‑analysis tools that need a lightweight, C++‑based inference engine. The packs are suitable for research projects and non‑commercial use, or for commercial use when the Apache‑2.0 pack is chosen.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 0.3 GB | 0.8 GB | Fits | Get file → |
All packs are f16 and have file sizes from 0.01 GB to 0.25 GB. For 8 GB VRAM, any pack will fit comfortably. If memory is limited, choose the 0.01 GB or 0.02 GB pack; for higher accuracy, use the 0.25 GB pack.
What GPU do you need for face detect?
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 (0.3 GB file, about 0.8 GB in use).
Which face detect quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 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 face detect
How much VRAM does face detect need?
About 0.6 GB at its main file with an 8K context window. That is the 0.1 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 face detect on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of face detect GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, file is 0.1 GB, file is 0.2 GB, file is 0.2 GB and 1 more.
Where can I download face detect GGUF?
The files are on Hugging Face in the mudler/face-detect-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does face detect use?
Hugging Face lists the license as other. 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 this model on 8 GB VRAM?
Yes. All packs are under 0.3 GB and use only 0.5–0.8 GB of VRAM at 8k context.
Is the model licensed for commercial use?
Only the yunet‑sface.gguf pack is Apache‑2.0. The other packs are non‑commercial research‑only.
Does the model support other languages?
No. The model is purely visual and has no language capabilities.