BGE M3 Ko measured on 13 of 194 Embeddings benchmarks13
BenchmarkByScoreRank
Reranking2
Other11
No benchmark matches
price not verifiedprice
37.5MTEB Thai v1
Sep 2024released
1,024Dimensions
8K tokensMax input
en, koLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+4%—$0.01Languages: not verified+1nOpenKURE v2+8%——nBetterKURE v3Open+7%——Memory (4-bit): 0.3 GB → 0.7 GBnBetterKURE Sparse BaseOpen+6%——Memory (4-bit): 0.3 GB → 0.4 GBsBetterComsat Embed Ko 8B PreviewOpen+5%——Memory (4-bit): 0.3 GB → 4.5 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+4%—$0.01Languages: not verified+1nKURE v2Open+8%——nKURE v3Open+7%——Memory (4-bit): 0.3 GB → 0.7 GBnKURE Sparse BaseOpen+6%——Memory (4-bit): 0.3 GB → 0.4 GBsComsat Embed Ko 8B PreviewOpen+5%——Memory (4-bit): 0.3 GB → 4.5 GBRun 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 BGE M3 Ko cost?›
There is no per-unit API price: price not verified.
How good is BGE M3 Ko, and what is it best at?›
#84 of 192 in Embeddings.
Is BGE M3 Ko better than Llama Nemotron Embed VL 1B v2?›
On MTEB Korean v2 · Retrieval · multilingual (2 languages), BGE M3 Ko scores 75.2 vs 75.5 — about the same.
When was BGE M3 Ko released? Is there a newer version?›
Released 2024-09-17. It is the current version in its line.
Is BGE M3 Ko open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run BGE M3 Ko locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is BGE M3 Ko?›
BGE M3 Ko is an open-weights embeddings & retrieval model from dragonkue, released Sep 2024.
What are the best alternatives to BGE M3 Ko?›
Qwen 3 Embedding 8B (better), KURE v2 (open weights).