Splade v3 measured on 8 of 194 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
24MTEB Korean v2
Mar 2024released
1K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
NKo Embed ClsOpen×3.5——Memory (4-bit): 0.1 GB → 0.3 GBSPwC Embedding ExprOpen×3——Memory (4-bit): 0.1 GB → 0.3 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
LicenceCC BY-NC-SA 4.0no commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Splade v3 cost?›
There is no per-unit API price: price not verified.
How good is Splade v3, and what is it best at?›
#79 of 156 in Embeddings.
Is Splade v3 better than Sentence Croissant Alpha v0.3?›
On MTEB Korean v2 · Classification · Korean, Splade v3 scores 24 vs 24.8 — about the same.
When was Splade v3 released? Is there a newer version?›
Released 2024-03-08. It is the current version in its line.
Is Splade v3 open source?›
Yes, the weights are open (cc-by-nc-sa-4.0 licence).
Can I run Splade v3 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Splade v3?›
Splade v3 is an open-weights embeddings & retrieval model from naver, released Mar 2024.
What are the best alternatives to Splade v3?›
Qwen 3 Embedding 8B (better), Ko Embed Cls (open weights).