Splade v2 Distil measured on 8 of 194 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
22.8MTEB Korean v2
Apr 2023released
1K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
sBetterAll MiniLM L6 v2unstatedOpen×2.9—$0.005Max input: 1K tokens → 0K tokenscOpenF2LLM v2 8Bunstated×25.4——Memory (4-bit): 0 GB → 4.5 GB
BetterQwen 3 Embedding 8BunstatedOpen×21.6—$0.01Languages: not verified+1iBetterMultilingual E5 Large InstructunstatedOpen×21.4—$0.01Memory (4-bit): 0 GB → 0.3 GBBetterQwen 3 Embedding 0.6BunstatedOpen×19.6—$0.01Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
sAll MiniLM L6 v2unstatedOpen×2.9—$0.005Max input: 1K tokens → 0K tokensQwen 3 Embedding 8BunstatedOpen×21.6—$0.01Languages: not verified+1iMultilingual E5 Large InstructunstatedOpen×21.4—$0.01Memory (4-bit): 0 GB → 0.3 GBQwen 3 Embedding 0.6BunstatedOpen×19.6—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen×21.6—$0.02Languages: not verified+1ModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen×25.4——Memory (4-bit): 0 GB → 4.5 GBcF2LLM v2 0.6BunstatedOpen×25.3——Memory (4-bit): 0 GB → 0.4 GBcF2LLM v2 1.7BunstatedOpen×24.9——Memory (4-bit): 0 GB → 1 GBcF2LLM v2 4BunstatedOpen×24.5——Memory (4-bit): 0 GB → 2.4 GB
Jina Embeddings v5 Text SmallunstatedOpen×22.7—$0.05Languages: not verified+1Run 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 v2 Distil cost?›
There is no per-unit API price: price not verified.
How good is Splade v2 Distil, and what is it best at?›
#93 of 156 in Embeddings.
Is Splade v2 Distil better than Opensearch Neural Sparse Encoding v2 Distill?›
On MTEB Korean v2 · Clustering · Korean, Splade v2 Distil scores 3.3 vs 4.4 — lower.
When was Splade v2 Distil released? Is there a newer version?›
Released 2023-04-18. It is the current version in its line.
Is Splade v2 Distil open source?›
Yes, the weights are open (cc-by-nc-sa-4.0 licence).
Can I run Splade v2 Distil locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Splade v2 Distil?›
Splade v2 Distil is an open-weights embeddings & retrieval model from naver, released Apr 2023.
What are the best alternatives to Splade v2 Distil?›
All MiniLM L6 v2 (better), F2LLM v2 8B (open weights).