SAVRN Model Hub · Comparisons
siglip2-giant-opt-patch16-384 vs siglip2-so400m-patch14-384
Siglip2-giant-opt-patch16-384 has 1.9B parameters and siglip2-so400m-patch14-384 has 1.1B parameters; both are released under Apache License 2.0; at 16-bit, siglip2-giant-opt-patch16-384 needs about 4.5 GB (1x MI300X from $1.85 an hour) and siglip2-so400m-patch14-384 about 2.7 GB (1x MI300X from $1.85 an hour).
| Field | siglip2-giant-opt-patch16-384 google/siglip2-giant-opt-patch16-384 | siglip2-so400m-patch14-384 google/siglip2-so400m-patch14-384 |
|---|---|---|
| Publisher | ||
| Task | Zero shot image classification | Zero shot image classification |
| Modality | Other | Other |
| Parameters, as reported | 1.9B parameters | 1.1B parameters |
| Architecture | siglip | siglip |
| Library | transformers | transformers |
| Context length | Not stated | Not stated |
| Repository size | 7.5 GB | 4.6 GB |
| Artifact formats | safetensors | safetensors |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 4.5 GB | 2.7 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 1.1 GB | 0.7 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | a713301b217d | e8e487298228 |
| Downloads reported by the hub | 2.4M | 1M |
| 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 siglip2-giant-opt-patch16-384
The download is 7.5 GB across 11 files, but the 16-bit copy needs 4.5 GB of memory and 4-bit needs 1.1 GB, so budget disk and memory separately for siglip2-giant-opt-patch16-384. Google publishes it for zero-shot image classification and image-text retrieval, and as the vision tower in front of a language model. On the cheapest slot we track, one MI300X with 192 GB at $1.85 an hour on demand, 4.5 GB is a sliver, so it rides beside the model it feeds.
No context length applies to an encoder, so the license carries the deployment questions: Apache License 2.0 permits commercial use, modification and redistribution, with notices kept and significant changes stated. What a buyer should check is the three papers the file cites, arXiv:2502.14786, arXiv:2303.15343 and arXiv:2209.06794, for the training recipe, and that the 1,152 hidden size and 256,000-entry vocabulary match the model it will feed.
SAVRN's Notes on siglip2-so400m-patch14-384
Most deployments will not serve this model on its own. Google describes it as a vision encoder for VLMs as well as a standalone tool for zero-shot image classification and image-text retrieval, and at 2.7 GB of memory at 16-bit, 2.3 GB of it weights, it sits beside whatever language model it feeds. The cheapest host we list, one MI300X with 192 GB at $1.85 an hour, runs it with room for the rest of the stack. Twenty-seven layers, a 1,152 hidden size and a 256,000-entry vocabulary make up the 1.1B parameters.
Apache 2.0 allows commercial use, modification and redistribution, provided the license and copyright notices stay and significant changes are stated, and it includes a patent grant. Before committing, note that no context length is listed, the files total 4.58 GB in safetensors only, and the design rests on three papers in our records: arXiv:2502.14786, arXiv:2303.15343 and arXiv:2209.06794.
Questions
Which is larger, siglip2-giant-opt-patch16-384 or siglip2-so400m-patch14-384?
siglip2-giant-opt-patch16-384 (1.9B parameters) is larger than siglip2-so400m-patch14-384 (1.1B parameters), by the parameter counts their publishers report.
Which is cheaper to run, siglip2-giant-opt-patch16-384 or siglip2-so400m-patch14-384?
At 4-bit, siglip2-giant-opt-patch16-384 fits on 1x MI300X from $1.85 an hour and siglip2-so400m-patch14-384 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use siglip2-giant-opt-patch16-384 commercially?
Yes. siglip2-giant-opt-patch16-384 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 siglip2-so400m-patch14-384 commercially?
Yes. siglip2-so400m-patch14-384 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.