dinov3-vitl16-pretrain-lvd1689m needs about 1.2 GB of memory at F16 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU.
DINOv3 ViT-L/16 (lvd1689m) vision encoder in GGUF f16
The DINOv3 ViT-L/16 (lvd1689m) model is provided as a GGUF f16 file for use with trellis2cpp and ggml runtimes. It produces image conditioning features for the TRELLIS.2 image‑to‑3D pipeline. The weights are byte‑identical to Meta’s official release.
Good at
- Image feature extraction
- Vision‑to‑3D conditioning
- Compatibility with trellis2cpp
Limits
- No language support
- No vision‑to‑text generation
- License requires attribution
Best for
- 3D reconstruction pipelines
- Image embedding generation
- Vision‑based conditioning for LLMs
Who it’s for. Developers building vision‑to‑3D or vision‑conditioned language models. Suitable for projects that require a pre‑trained vision encoder with a small memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.6 GB | 1.2 GB | Fits | Get file → |
The only available quant is f16, file size 0.61 GB. It requires about 1.2 GB of VRAM at 8 k context. For 8 GB VRAM, this model fits comfortably. No other quantizations are provided.
What GPU do you need for dinov3-vitl16-pretrain-lvd1689m?
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 F16 (0.6 GB file, about 1.2 GB in use).
Which dinov3-vitl16-pretrain-lvd1689m quant should you choose?
F16 (0.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about dinov3-vitl16-pretrain-lvd1689m
How much VRAM does dinov3-vitl16-pretrain-lvd1689m need?
About 1.2 GB at F16 with an 8K context window. That is the 0.6 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 dinov3-vitl16-pretrain-lvd1689m on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of dinov3-vitl16-pretrain-lvd1689m GGUF?
It depends on the quant: F16 is 0.6 GB.
Where can I download dinov3-vitl16-pretrain-lvd1689m GGUF?
The files are on Hugging Face in the LocalAI-io/dinov3-vitl16-pretrain-lvd1689m-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 dinov3-vitl16-pretrain-lvd1689m 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, the f16 quant requires approximately 1.2 GB of VRAM at 8 k context, well within an 8 GB budget.
Does this model support text generation?
No, it is a vision encoder only and does not generate text.
What license applies to this model?
It is redistributed under Meta’s DINOv3 License, requiring attribution and compliance with the agreement.