Why did we open-source our inference engine? Read the post

← Catalog

Marqo/marqo-ecommerce-embeddings-B

Open comparison →

Primitive: /encode · Encode · SigLIP

In this work, we introduce two state-of-the-art embedding models for ecommerce products: Marqo-Ecommerce-B and Marqo-Ecommerce-L.

MultimodalDense

Overview

Hardware: — drives latency, throughput & cost

Size203M params
Tasks /encode
Licenseapache-2.0
Latency
Throughput
Cost /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Embedding

Output typesDense
Dimensionsdense: 768
Max sequence length64
Inputstext · image

Benchmarks

Flickr30kI2TRetrieval

general retrieval en

Image-to-text retrieval: retrieve captions from images

Corpus: 31,783 Queries: 1,000
Quality
ndcg at 10 0.6078
map at 10 0.4872
mrr at 10 0.7767
Reference →

Open source inference for agents

Open-source inference for the models behind your agents. Run it yourself, or let us run it for you.

Github 2.8K

Contact us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.