google/embeddinggemma-300m

Architecture

Parameters

300M

Tasks

Encode

Outputs

Dense

Dimensions

Dense: 768

Max Sequence Length

2,048 tokens

License

—

Benchmarks

medical retrieval en

Quality

ndcg at 10 0.3876

map at 10 0.1471

mrr at 10 0.5895

Performance RTX-4090 b1 c16

Corpus TPS 79.6K

Corpus p50 55.7ms

Query TPS 1.9K

Query p50 27.8ms

Cut API costs by 50x, boost quality with 85+ SOTA models, and keep your data in your own cloud.