google/siglip2-base-patch16-224
Primitive: /encode · Encode ·
SigLIP
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features.
MultimodalDense
Overview
Hardware: — drives latency, throughput & cost
| Size | 375M params |
|---|---|
| Tasks | /encode |
| License | apache-2.0 |
| Latency | 69 ms |
| Throughput | 1.6K tok/s |
| Cost | $0.140 /1M tok |
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Embedding
| Output types | Dense |
|---|---|
| Dimensions | dense: 768 |
| Max sequence length | 64 |
| Inputs | text · image |
Benchmarks
Flickr30kI2TRetrieval
Image-to-text retrieval: retrieve captions from images
Corpus: 31,783 Queries: 1,000
Quality
ndcg at 10 0.8157
map at 10 0.7255
mrr at 10 0.9302
Performance L4 b1 c8
Corpus 1.6K tok/s
Corpus p50 68.5ms
Query 13.0 mpix/s
Query p50 99.0ms
Compare (0)Compare →