sam 3d body dinov3 needs about 1.3 GB of memory at F32 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.2 GB (F32) to 3.4 GB (F32).
SAM 3D Body DINOv3 – 3D body mesh and pose estimation
SAM 3D Body DINOv3 is a 0.841 billion‑parameter model that generates 3D body meshes, joints, pose parameters and camera translation from an image and a bounding box. It is a GGUF conversion of Meta’s facebook/sam-3d-body-dinov3 and runs with sam3d.cpp on CPU or Vulkan.
Good at
- 3D body mesh generation
- Pose parameter extraction
- Camera translation estimation
Limits
- Requires sam3d.cpp, not llama.cpp
- No low‑bit quantization variants
- Only one person per request
Best for
- AR/VR body tracking
- Game character animation
- Medical posture analysis
Who it’s for. Developers building 3D body reconstruction pipelines or applications that need accurate body meshes from images. It is suitable for CPU or Vulkan GPU inference without Python or CUDA dependencies.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F32 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| F32 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| F32 | 3.4 GB | 4.3 GB | Fits | Get file → |
For 8 GB VRAM, the 0.23 GB F32 file uses about 0.8 GB memory at 8 k context. The 0.69 GB file uses about 1.3 GB memory. For larger memory budgets, the 3.36 GB file uses about 4.3 GB memory. Choose the smallest file that fits your VRAM and RAM limits.
What GPU do you need for sam 3d body dinov3?
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 F32 (0.7 GB file, about 1.3 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (3.4 GB file, about 4.3 GB in use).
Which sam 3d body dinov3 quant should you choose?
F32 (0.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is F32 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about sam 3d body dinov3
How much VRAM does sam 3d body dinov3 need?
About 1.3 GB at F32 with an 8K context window. That is the 0.7 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 sam 3d body dinov3 on an 8 GB GPU?
Yes, with F32: the 3.4 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sam 3d body dinov3 GGUF?
It depends on the quant: F32 is 0.2 GB, F32 is 0.7 GB, F32 is 3.4 GB.
Where can I download sam 3d body dinov3 GGUF?
The files are on Hugging Face in the LocalAI-io/sam-3d-body-dinov3-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 sam 3d body dinov3 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 SAM 3D Body DINOv3 on 8 GB VRAM?
Yes, the 0.23 GB F32 file uses approximately 0.8 GB memory at 8 k context, fitting within 8 GB VRAM.
Does this model support multiple people in one image?
No, it supports only one selected person per request with an explicit bounding box.
Is there a low‑bit quantized version available?
No, this release contains only F32 quantizations; no Q4 or Q8 variants are provided.