Multi Qa MiniLM L6 Cos v1 measured on 18 of 261 Embeddings benchmarks18
BenchmarkByScoreRank
Reranking10
Other8
No benchmark matches
price not verifiedprice
47MTEB English v2
Aug 2021released
384Dimensions
1K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+20%—$0.002Languages: not verified+1
OpenNV Embed v1unstated+23%——Memory (4-bit): 0 GB → 4.7 GBiBetterE5 Base v2unstatedOpen+6%—$0.005Memory (4-bit): 0 GB → 0.1 GBtBetterGte BaseunstatedOpen+5%—$0.005Memory (4-bit): 0 GB → 0.1 GB
BetterBge Base En v1.5unstatedOpen+4%—$0.005Memory (4-bit): 0 GB → 0.1 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+20%—$0.002Languages: not verified+1iE5 Base v2unstatedOpen+6%—$0.005Memory (4-bit): 0 GB → 0.1 GBtGte BaseunstatedOpen+5%—$0.005Memory (4-bit): 0 GB → 0.1 GBBge Base En v1.5unstatedOpen+4%—$0.005Memory (4-bit): 0 GB → 0.1 GB
Qwen 3 Embedding 8BunstatedOpen+21%—$0.01Languages: not verified+1ModelScoreCostPriceWhat changes
NV Embed v1unstatedOpen+23%——Memory (4-bit): 0 GB → 4.7 GBmNemotron 3 Embed 8B LegalOpen+23%——Memory (4-bit): 0 GB → 4.8 GBNemotron 3 Embed 8B BF16Open+23%——Memory (4-bit): 0 GB → 4.8 GBNV Embed v2unstatedOpen+23%——Memory (4-bit): 0 GB → 4.7 GBaGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+23%——Memory (4-bit): 0 GB → 6.3 GBModelScoreCostPriceWhat changes
sParaphrase Multilingual Mpnet Base v2unstatedOpen+9%——Max input: 1K tokens → 0K tokens+1sParaphrase Multilingual MiniLM L12 v2unstatedOpen+7%——Max input: 1K tokens → 0K tokens+1sLaBSEunstatedOpen+7%——Max input: 1K tokens → 0K tokens+1sStatic Similarity Mrl Multilingual v1unstatedOpen+7%——Max input: not verified+1sGtr T5 LargeunstatedOpen+4%——Memory (4-bit): 0 GB → 0.2 GBsSentence T5 LargeunstatedOpen+3%——Max input: 1K tokens → 0K tokens+1sAll MiniLM L12 v2unstatedOpensame—$0.005Max input: 1K tokens → 0K tokenssAll Mpnet Base v2unstatedOpen-2%—$0.005Max input: 1K tokens → 0K tokens+1All sentence-transformers 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
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalMTEB Dutch v1 · STS · Dutch57.6#99
FAQ
How much does Multi Qa MiniLM L6 Cos v1 cost?›
There is no per-unit API price: price not verified.
How good is Multi Qa MiniLM L6 Cos v1, and what is it best at?›
#98 of 223 in Embeddings.
Is Multi Qa MiniLM L6 Cos v1 better than LLM2Vec Mistral 7B Instruct v2 Mntp Unsup Simcse?›
On MTEB Dutch v1 · Reranking · Dutch, Multi Qa MiniLM L6 Cos v1 scores 75.5 vs 75.6 — about the same.
When was Multi Qa MiniLM L6 Cos v1 released? Is there a newer version?›
Released 2021-08-30. It is the current version in its line.
Is Multi Qa MiniLM L6 Cos v1 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Multi Qa MiniLM L6 Cos v1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Multi Qa MiniLM L6 Cos v1?›
Multi Qa MiniLM L6 Cos v1 is an open-weights embeddings & retrieval model from sentence-transformers, released Aug 2021.
What are the best alternatives to Multi Qa MiniLM L6 Cos v1?›
EmbeddingGemma 300M (better), NV Embed v1 (open weights).