No matches. Try a model format, tool name or error.
What is the best open embedding model?
Compare the embedding records below for language coverage and input requirements. Test retrieval on your documents; catalog order does not measure search quality.
Recorded CPU embedding runs
Vector output was observed on one CPU host. Retrieval quality was not tested.
Model from Hugging Face for feature extraction: Qwen/Qwen3-Embedding-0.6B · sentence transformers
License
apache-2.0. Permissive open license: commercial use, modification, and redistribution are permitted. License details
Hosting
1 hosted file. Inspect the file record for current availability. 12 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: feature extraction. Listed formats: safetensors. Recorded license: apache-2.0. This listing does not measure quality or prove runtime support.
14 hosted files. Inspect the file record for current availability. 15 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: sentence similarity. Listed formats: safetensors. This listing does not measure quality or prove runtime support.
Model from Hugging Face for sentence similarity: Alibaba-NLP/gte-base-en-v1.5 · transformers
License
apache-2.0. Permissive open license: commercial use, modification, and redistribution are permitted. License details
Hosting
16 hosted files. Inspect the file record for current availability. 18 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: sentence similarity. Listed formats: safetensors, onnx. Recorded license: apache-2.0. This listing does not measure quality or prove runtime support.
11 hosted files. Inspect the file record for current availability. 15 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: feature extraction. Listed formats: safetensors. This listing does not measure quality or prove runtime support.
8 hosted files. Inspect the file record for current availability. 12 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: sentence similarity. Listed formats: safetensors. This listing does not measure quality or prove runtime support.
9 hosted files. Inspect the file record for current availability. 12 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: sentence similarity. Listed formats: safetensors. This listing does not measure quality or prove runtime support.
6 hosted files. Inspect the file record for current availability. 9 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: sentence similarity. Listed formats: safetensors. This listing does not measure quality or prove runtime support.
Model from Hugging Face for feature extraction: laion/clap-htsat-unfused · transformers
License
apache-2.0. Permissive open license: commercial use, modification, and redistribution are permitted. License details
Hosting
3 hosted files. Inspect the file record for current availability. 10 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: feature extraction. Recorded license: apache-2.0. This listing does not measure quality or prove runtime support.
Model from Hugging Face for feature extraction: BAAI/bge-multilingual-gemma2 · sentence transformers
License
gemma. Commercial use is permitted with obligations: Gemma terms: commercial use allowed subject to Google's prohibited-use policy. License details
Hosting
13 hosted files. Inspect the file record for current availability. 24 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: feature extraction. Listed formats: safetensors. Recorded license: gemma. This listing does not measure quality or prove runtime support.
8 hosted files. Inspect the file record for current availability. 86 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: sentence similarity. Listed formats: safetensors, onnx. This listing does not measure quality or prove runtime support.
5 hosted files. Inspect the file record for current availability. 9 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: feature extraction. Listed formats: safetensors. This listing does not measure quality or prove runtime support.
8 hosted files. Inspect the file record for current availability. 11 files listed upstream.
Why listed
The catalog lists it as an embedding model for text search. Recorded task: sentence similarity. Listed formats: safetensors, onnx. This listing does not measure quality or prove runtime support.