LGAI Embedding Preview measured on 8 of 261 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
66.2MTEB English v2
Jun 2025released
4,096Dimensions
33K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →Strong at
Alternatives?
ModelScoreCostPriceWhat changes
IOpenICT TIME And Querit Embedding v1unstatedsame——Languages: not verifiedaOpenGiga Embeddings Instructunstated-3%——Max input: 33K tokens → 4K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
IICT TIME And Querit Embedding v1unstatedOpensame——Languages: not verifiedaGiga Embeddings InstructunstatedOpen-3%——Max input: 33K tokens → 4K tokensRun it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 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 LGAI Embedding Preview cost?›
There is no per-unit API price: self-host only.
Is LGAI Embedding Preview free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is LGAI Embedding Preview, and what is it best at?›
#9 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
Is LGAI Embedding Preview better than LCO Embedding Omni 7B?›
On MTEB English v2 · Summarization · English, LGAI Embedding Preview scores 38.9 vs 39.7 — about the same.
When was LGAI Embedding Preview released? Is there a newer version?›
Released 2025-06-11. It is the current version in its line.
Is LGAI Embedding Preview open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run LGAI Embedding Preview locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is LGAI Embedding Preview?›
LGAI Embedding Preview is an open-weights embeddings & retrieval model from annamodels, released Jun 2025.
What are the best alternatives to LGAI Embedding Preview?›
ICT TIME And Querit Embedding v1 (open weights).