SAVRN Model Hub · Comparisons
dinov2-base vs dinov3-vitl16-pretrain-lvd1689m
Dinov2-base has 87M parameters and dinov3-vitl16-pretrain-lvd1689m has 303M parameters; dinov2-base is released under Apache License 2.0 and dinov3-vitl16-pretrain-lvd1689m under other; at 16-bit, dinov2-base needs about 0.2 GB (1x MI300X from $1.85 an hour) and dinov3-vitl16-pretrain-lvd1689m about 0.7 GB (1x MI300X from $1.85 an hour).
| Field | dinov2-base facebook/dinov2-base | dinov3-vitl16-pretrain-lvd1689m camenduru/dinov3-vitl16-pretrain-lvd1689m |
|---|---|---|
| Publisher | AI at Meta | Camenduru |
| Task | Image feature extraction | Image feature extraction |
| Modality | Other | Other |
| Parameters, as reported | 87M parameters | 303M parameters |
| Architecture | Dinov2Model | DINOv3ViTModel |
| Library | transformers | transformers |
| Context length | Not stated | Not stated |
| Repository size | 692.7 MB | 1.2 GB |
| Artifact formats | safetensors, pytorch | safetensors |
| License | apache-2.0 | other |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.2 GB | 0.7 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.1 GB | 0.2 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | f9e44c814b77 | 3c276edd87d6 |
| Downloads reported by the hub | 3.4M | 738.6k |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on dinov2-base
Nothing about this one strains a card. The 16-bit weights load in 0.2 GB, and the cheapest option on the page is one MI300X with 192 GB at $1.85 an hour, so share the card; the image batch sets the bill, not the encoder. What comes out is a feature vector, not an answer, which puts its 87M parameters and 768-wide hidden state ahead of your own classifier or retrieval index.
Nothing in the license slows a deployment: Apache 2.0 covers commercial use, modification and redistribution as long as the notices stay attached, so a fine-tuned head ships with the encoder in a product. Two things to confirm: the page lists no reported evaluations, so your own held-out images are the benchmark, and the publisher's team did not write the model card, so the paper it cites, arXiv:2304.07193, is the record of training. Weights last updated January 17, 2024.
SAVRN's Notes on dinov3-vitl16-pretrain-lvd1689m
What does a vision model that returns features instead of answers earn its rack space with? For dinov3-vitl16-pretrain-lvd1689m the answer is embeddings: it turns a picture into a feature vector that a downstream classifier or search index consumes. At 303 million parameters and 24 layers, the 16-bit weights are 0.6 GB and need 0.7 GB of memory; 8-bit drops that to 0.4 GB. One MI300X at $1.85 an hour is the cheapest card in our table and far more than the model needs, so the decision is about images per hour, not fitting weights.
The license field reads other with no summary attached, and the listed publisher is Camenduru while the weights derive from facebook/dinov3-vit7b16-pretrain-lvd1689m, so trace the terms to that source before any commercial deployment. The paper is arXiv:2508.10104. There is no context length to size, so your check is image throughput per card.
Questions
Which is larger, dinov2-base or dinov3-vitl16-pretrain-lvd1689m?
dinov3-vitl16-pretrain-lvd1689m (303M parameters) is larger than dinov2-base (87M parameters), by the parameter counts their publishers report.
Which is cheaper to run, dinov2-base or dinov3-vitl16-pretrain-lvd1689m?
At 4-bit, dinov2-base fits on 1x MI300X from $1.85 an hour and dinov3-vitl16-pretrain-lvd1689m on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use dinov2-base commercially?
Yes. dinov2-base is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.