Sentence T5 Xl measured on 3 of 261 Embeddings benchmarks3
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
86.1MTEB English v2
Mar 2024released
0K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
KQZhou EmbeddingunstatedOpen+7%——Memory (4-bit): 0.7 GB → 4.2 GBiJasper Token Compression 600MunstatedOpen+5%——KNano Em1 0.6B v2.1unstatedOpen+4%——ModelScoreCostPriceWhat changes
sGtr T5 LargeunstatedOpensame——sSentence T5 BaseunstatedOpensame——sSentence T5 XxlunstatedOpensame——Memory (4-bit): 0.7 GB → 2.9 GBsSentence T5 LargeunstatedOpen-1%——sGtr T5 BaseunstatedOpen-3%——sAll Mpnet Base v2unstatedOpen-4%—$0.005sAll MiniLM L12 v2unstatedOpen-4%—$0.005sAll MiniLM L6 v2unstatedOpen-4%—$0.005All 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 & RetrievalFAQ
How much does Sentence T5 Xl cost?›
There is no per-unit API price: self-host only.
Is Sentence T5 Xl free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Sentence T5 Xl, and what is it best at?›
#55 of 238 in Embeddings.
Is Sentence T5 Xl better than Voyage 3 M Exp?›
On MTEB English v2 · Pair Classification · English, Sentence T5 Xl scores 86.1 vs 86.1 — about the same.
When was Sentence T5 Xl released? Is there a newer version?›
Released 2024-03-27. It is the current version in its line.
Is Sentence T5 Xl open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Sentence T5 Xl locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Sentence T5 Xl?›
Sentence T5 Xl is an open-weights embeddings & retrieval model from sentence-transformers, released Mar 2024.
What are the best alternatives to Sentence T5 Xl?›
Bge En Icl (better), QZhou Embedding (open weights).