Model reference · open weights
vit_base_patch16_dinov3_qkvb.lvd is an open-weight embedding model from timm, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Model card for vitbasepatch16dinov3qkvb.lvd1689m A DINOv3 ViT model image feature encoder. Distilled on LVD-1689M from the DINOv3 ViT-7B model. Model Notes The original model weights ended up with all QKV projection biases being zeroes. For timm, have disabled the QKV bias (qkvbias=False) for the models and not loaded the zero weights. For some model sizes there are variants with qkvb in the name that have the bias enabled (qkvbias=True), but zero, to match the behaviour of transformers and original models. The original models keep RoPE periods as a persistent bfloat16 buffer. timm generates float32 periods at init. This results in some numerical differences, however the timm approach should be less problematic running on devices without bfloat16 support, and appears to work as well if not slightly better for fine-tuning. model.rope.periods = model.rope.periods.to(torch.bfloat16).to(torch.float32) will truncate the periods to bfloat16 and result in matching outputs. Model Details - Model Type: Image Feature Encoder - Model Stats: - Params (M): 85.7 - GMACs: 23.6 - Activations (M): 34.1 - Image size: 256 x 256 - Original: https://github.com/facebookresearch/dinov3 - License: DINOv3 - Dataset: LVD-1689M - Papers: - DINOv3: https://arxiv.org/abs/2508.10104 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 - PyTorch Image Models: https://github.com/huggingface/pytorch-image-models Model Usage Image Classification Feature Map Extraction Image Embeddings Model Comparison See the associated paper for details on the evaluation protocols Results for ViT backbones pretrained (or distilled) on web (LVD-1689M) Results for ConvNeXt backbones distilled on web (LVD-1689M) Results for ViT backbones pretrained (or distilled) on satellite (SAT-493M) (GEO-Bench) Classification (GEO-Bench) Segmentation Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | timm |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 86M |
| Variants | 1 |
| Runs with | timm |
| Released | 2025-09-17 |
| Popularity | 141k downloads / month |
| Likes | 1 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| vit_base_patch16_dinov3_qkvb.lvd1689m | 86M | BF16 | ~0.2 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys vit-base-patch16-dinov3-qkvb-lvd for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vit-base-patch16-dinov3-qkvb-lvd below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"vit-base-patch16-dinov3-qkvb-lvd","input":"text to embed"}'
Details
Trained / evaluated on
Tags
Papers
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Explore