SAVRN Model Hub · Comparisons
dinov2-small vs vit_small_patch14_dinov2.lvd142m
Dinov2-small has 22M parameters and vit_small_patch14_dinov2.lvd142m has 22M parameters; both are released under Apache License 2.0; at 16-bit, dinov2-small needs about 0.1 GB (1x MI300X from $1.85 an hour) and vit_small_patch14_dinov2.lvd142m about 0.1 GB (1x MI300X from $1.85 an hour).
| Field | dinov2-small facebook/dinov2-small | vit_small_patch14_dinov2.lvd142m timm/vit_small_patch14_dinov2.lvd142m |
|---|---|---|
| Publisher | AI at Meta | PyTorch Image Models |
| Task | Image feature extraction | Image feature extraction |
| Modality | Other | Other |
| Parameters, as reported | 22M parameters | 22M parameters |
| Architecture | Dinov2Model | Not stated |
| Library | transformers | timm |
| Context length | Not stated | Not stated |
| Repository size | 176.6 MB | 176.5 MB |
| Artifact formats | safetensors, pytorch | safetensors, pytorch |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.1 GB | 0.1 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0 GB | 0 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | ed25f3a31f01 | 4610ca143709 |
| Downloads reported by the hub | 3.2M | 1.2M |
| 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-small
What do you do with a 192 GB card and a model that needs 0.1 GB of it? That is the pairing here: one MI300X at $1.85 an hour is the cheapest setup we list, and this 22M parameter encoder, 176.6 MB on disk, rides along on whatever you already run. We would put it on a camera feed or an ingest queue where every image needs a fixed feature vector and 12 layers with a 384-wide hidden state are the whole machine.
Age is the first thing to weigh: released July 31, 2023, last updated September 6, 2023, nothing since. The page lists no reported evaluations, so the paper it cites, arXiv:2304.07193, and your own labeled images are all you have to decide on. Keep the notices and Apache 2.0 lets the encoder and whatever head you train on it be sold inside a product.
Questions
Which is larger, dinov2-small or vit_small_patch14_dinov2.lvd142m?
dinov2-small (22M parameters) is larger than vit_small_patch14_dinov2.lvd142m (22M parameters), by the parameter counts their publishers report.
Which is cheaper to run, dinov2-small or vit_small_patch14_dinov2.lvd142m?
At 4-bit, dinov2-small fits on 1x MI300X from $1.85 an hour and vit_small_patch14_dinov2.lvd142m on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use dinov2-small commercially?
Yes. dinov2-small 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.
Can I use vit_small_patch14_dinov2.lvd142m commercially?
Yes. vit_small_patch14_dinov2.lvd142m 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.