self-host onlyprice
84.4MTEB Korean v2
Sep 2026released
1,024Dimensions
8K tokensMax input
koLanguages
Alternatives?
ModelScoreCostPriceWhat changes
SOpenPwC Embedding Expr-13%——Max input: 8K tokens → 1K tokens
OpenQwen 3 Embedding 8Bunstated-18%—$0.01Languages: not verified+1cOpenF2LLM v2 8Bunstated-20%——Memory (4-bit): 0.3 GB → 4.5 GBOpenQwen 3 Embedding 4Bunstated-20%—$0.02Languages: not verified+1OpenGte Qwen2 7B Instructunstated-21%——Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
SPwC Embedding ExprOpen-13%——Max input: 8K tokens → 1K tokensQwen 3 Embedding 8BunstatedOpen-18%—$0.01Languages: not verified+1cF2LLM v2 8BunstatedOpen-20%——Memory (4-bit): 0.3 GB → 4.5 GBQwen 3 Embedding 4BunstatedOpen-20%—$0.02Languages: not verified+1Gte Qwen2 7B InstructunstatedOpen-21%——Languages: not verified+1ModelScoreCostPriceWhat changes
NKo Embed v0Open-31%——NJa Embed StsOpenn/a——Max input: 8K tokens → 1K tokensNKo Embed NliOpenn/a——All NGA-KR 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 Ko Embed Cls cost?›
There is no per-unit API price: self-host only.
Is Ko Embed Cls free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ko Embed Cls, and what is it best at?›
#1 of 156 in Embeddings.
Is Ko Embed Cls better than PwC Embedding Expr?›
On MTEB Korean v2 · Classification · Korean, Ko Embed Cls scores 84.4 vs 73 — higher.
When was Ko Embed Cls released? Is there a newer version?›
Released 2026-09-10. It is the current version in its line.
Is Ko Embed Cls open source?›
Yes, the weights are open (MIT licence).
Can I run Ko Embed Cls locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Ko Embed Cls?›
Ko Embed Cls is an open-weights embeddings & retrieval model from NGA-KR, released Sep 2026.
What are the best alternatives to Ko Embed Cls?›
PwC Embedding Expr (open weights).