Bge Multilingual Gemma2
Jul 2024
Bge Multilingual Gemma2Compare inon
Bge Multilingual Gemma2 measured on 34 of 261 Embeddings benchmarks34
BenchmarkByScoreRank
Retrieval5
Reranking11
Other18
No benchmark matches
Alternatives?
ModelScoreCostPriceWhat changes
CheaperQwen 3 Embedding 8BunstatedOpen+47%-91%$0.01
BetterEmbeddingGemma 300MunstatedOpen+18%-98%$0.002Max input: 8K tokens → 2K tokenscOpenF2LLM v2 8Bunstated×2.3——
CheaperJina Embeddings v5 Text NanounstatedOpen+44%-82%$0.02iCheaperMultilingual E5 Large InstructunstatedOpen+42%-91%$0.01Max input: 8K tokens → 1K tokensModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+47%-91%$0.01Jina Embeddings v5 Text NanounstatedOpen+44%-82%$0.02iMultilingual E5 Large InstructunstatedOpen+42%-91%$0.01Max input: 8K tokens → 1K tokensJina Embeddings v5 Text SmallunstatedOpen+40%-55%$0.05Qwen 3 Embedding 4BunstatedOpen+37%-82%$0.02ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+18%-98%$0.002Max input: 8K tokens → 2K tokensQwen 3 Embedding 8BunstatedOpen+47%-91%$0.01iMultilingual E5 Large InstructunstatedOpen+42%-91%$0.01Max input: 8K tokens → 1K tokensQwen 3 Embedding 0.6BunstatedOpen+32%-91%$0.01Jina Embeddings v5 Text NanounstatedOpen+44%-82%$0.02ModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen×2.3——cF2LLM v2 14BunstatedOpen×2.3——Memory (4-bit): 5.5 GB → 8.4 GBcF2LLM v2 1.7BunstatedOpen×2.3——cF2LLM v2 4BunstatedOpen×2.3——cF2LLM v2 0.6BunstatedOpen×2.3——ModelScoreCostPriceWhat changes
Bge M3unstatedOpen-8%-91%$0.01Bge Small En v1.5unstatedOpen-91%-82%$0.02Max input: 8K tokens → 1K tokensBge Large En v1.5unstatedOpen-92%-91%$0.01Max input: 8K tokens → 1K tokensBge Base En v1.5unstatedOpen-92%-96%$0.005Max input: 8K tokens → 1K tokensBge En IclunstatedOpenn/a—$0.01Bge M3 UnsupervisedOpenn/a——Bge Large Zh v1.5Openn/a——Max input: 8K tokens → 1K tokensBge Small Zh v1.5Openn/a——Max input: 8K tokens → 1K tokensAll BAAI models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
Licencehttps://ai.google.dev/gemma/termscommercial use with conditions
Benchmarks
in Embeddings & RetrievalBEIR · Retrieval · English59.2#15
FAQ
How much does Bge Multilingual Gemma2 cost?›
$0.11 per 1M tokens.
Is Bge Multilingual Gemma2 free to use?›
There is no free API; it costs $0.11 per 1M tokens. The weights are open, so you can run it yourself.
How good is Bge Multilingual Gemma2, and what is it best at?›
#60 of 238 in Embeddings.
Is Bge Multilingual Gemma2 better than Bilingual Embedding Base?›
On MTEB Thai v1 · Clustering · Thai, Bge Multilingual Gemma2 scores 39.6 vs 40.2 — about the same.
When was Bge Multilingual Gemma2 released? Is there a newer version?›
Released 2024-07-25. It is the current version in its line.
Is Bge Multilingual Gemma2 open source?›
Yes, the weights are open (https://ai.google.dev/gemma/terms licence).
Can I run Bge Multilingual Gemma2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Bge Multilingual Gemma2?›
Bge Multilingual Gemma2 is an open-weights embeddings & retrieval model from BAAI, released Jul 2024.
What are the best alternatives to Bge Multilingual Gemma2?›
Qwen 3 Embedding 8B (cheaper), EmbeddingGemma 300M (better), F2LLM v2 8B (open weights).