Bge M3 Unsupervised
Jan 2024
Bge M3 UnsupervisedCompare inon
Bge M3 Unsupervised measured on 10 of 261 Embeddings benchmarks10
BenchmarkByScoreRank
Reranking5
Other5
No benchmark matches
price not verifiedprice
44.1RTEB French beta
Jan 2024released
1,024Dimensions
8K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
BetterBge M3unstatedOpen+7%—$0.01iBetterMultilingual E5 LargeunstatedOpen+7%—$0.01Max input: 8K tokens → 1K tokensiBetterMultilingual E5 Large InstructunstatedOpen+4%—$0.01Max input: 8K tokens → 1K tokensiBetterE5 Mistral 7B InstructunstatedOpen+3%—$0.022Memory (4-bit): 0.3 GB → 4.3 GB
BetterCohere Embed Multilingual v3.0unstated+7%——Max input: not verifiedModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Bge M3unstatedOpen+7%—$0.01iMultilingual E5 LargeunstatedOpen+7%—$0.01Max input: 8K tokens → 1K tokensiMultilingual E5 Large InstructunstatedOpen+4%—$0.01Max input: 8K tokens → 1K tokensiE5 Mistral 7B InstructunstatedOpen+3%—$0.022Memory (4-bit): 0.3 GB → 4.3 GBCohere Embed Multilingual v3.0unstated+7%——Max input: not verifiedModelScoreCostPriceWhat changes
Bge M3unstatedOpen+7%—$0.01iMultilingual E5 LargeunstatedOpen+7%—$0.01Max input: 8K tokens → 1K tokens
Snowflake Arctic Embed L v2.0unstatedOpen+6%——cF2LLM v2 8BunstatedOpen+5%——Memory (4-bit): 0.3 GB → 4.5 GBOSolon Embeddings Large 0.1unstatedOpen+4%——Max input: 8K tokens → 1K tokensModelScoreCostPriceWhat changes
Bge M3unstatedOpen+7%—$0.01Bge Large En v1.5unstatedOpen-38%—$0.01Max input: 8K tokens → 1K tokensBge Base En v1.5unstatedOpen-45%—$0.005Max input: 8K tokens → 1K tokensBge Small En v1.5unstatedOpen-56%—$0.02Max input: 8K tokens → 1K tokensBge En IclunstatedOpenn/a—$0.01Memory (4-bit): 0.3 GB → 4.3 GBBge Multilingual Gemma2unstatedOpenn/a—$0.11Memory (4-bit): 0.3 GB → 5.5 GBBge 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) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Bge M3 Unsupervised cost?›
There is no per-unit API price: price not verified.
How good is Bge M3 Unsupervised, and what is it best at?›
#54 of 212 in Embeddings.
Is Bge M3 Unsupervised better than Tooka SBERT v2 Large?›
On MTEB Persian v2 · Reranking · Persian, Bge M3 Unsupervised scores 69.7 vs 69.9 — about the same.
When was Bge M3 Unsupervised released? Is there a newer version?›
Released 2024-01-30. It is the current version in its line.
Is Bge M3 Unsupervised open source?›
Yes, the weights are open (MIT licence).
Can I run Bge M3 Unsupervised locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Bge M3 Unsupervised?›
Bge M3 Unsupervised is an open-weights embeddings & retrieval model from BAAI, released Jan 2024.
What are the best alternatives to Bge M3 Unsupervised?›
Bge M3 (better).