EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.
Laya is a 421M decision model from Convai Innovations, fine-tuned from ModernBERT-large.
nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
EmbeddingGemma is a 300M parameter embedding model from Google.
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.
Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
Embedding model from BAAI mapping texts to vectors.
Sentence-transformers model that can be used for tasks like clustering or semantic search.
BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
A suite of text embedding models by Snowflake, optimized for performance.
State-of-the-art large embedding model from mixedbread.ai
Embedding models on very large sentence level datasets.
A high-performing open embedding model with a large token context window.