Nano Em1 0.6B v2 measured on 11 of 194 Embeddings benchmarks11
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
43.2MTEB English v2
Jul 2026released
1,024Dimensions
41K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →···
143All MiniLM L12 v243.7144Nano Em1 0.6B v243.2145Bilingual Embedding Base43.2Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+29%—$0.002Max input: 41K tokens → 2K tokens+1IOpenYuan Embedding 2.0 Enunstated+63%——Max input: 41K tokens → 33K tokens
BetterBge Base En v1.5unstatedOpen+27%—$0.005Max input: 41K tokens → 1K tokenstBetterGte BaseunstatedOpen+20%—$0.005Max input: 41K tokens → 1K tokensiBetterE5 Base v2unstatedOpen+15%—$0.005Max input: 41K tokens → 1K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+29%—$0.002Max input: 41K tokens → 2K tokens+1Bge Base En v1.5unstatedOpen+27%—$0.005Max input: 41K tokens → 1K tokenstGte BaseunstatedOpen+20%—$0.005Max input: 41K tokens → 1K tokensiE5 Base v2unstatedOpen+15%—$0.005Max input: 41K tokens → 1K tokens
Qwen 3 Embedding 8BunstatedOpen+61%—$0.01Max input: 41K tokens → 33K tokens+2ModelScoreCostPriceWhat changes
IYuan Embedding 2.0 EnunstatedOpen+63%——Max input: 41K tokens → 33K tokensQwen 3 Embedding 8BunstatedOpen+61%—$0.01Max input: 41K tokens → 33K tokens+2Qwen 3 Embedding 4BunstatedOpen+58%—$0.02Max input: 41K tokens → 33K tokens+2KQZhou EmbeddingunstatedOpen+55%——Max input: 41K tokens → 33K tokens+1iJasper Token Compression 600MunstatedOpen+53%——Max input: 41K tokens → 33K tokensModelScoreCostPriceWhat changes
KNano Em1 0.6B v2.1unstatedOpen+8%——Max input: 41K tokens → 8K tokensAll KiteFishAI 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
LicenceApache-2.0free for commercial use
History
2 versionsBenchmarks
in Embeddings & RetrievalBEIR · Mean over tasks · English40.6#145
BEIR · Retrieval · English40.6#145
FAQ
How much does Nano Em1 0.6B v2 cost?›
There is no per-unit API price: self-host only.
Is Nano Em1 0.6B v2 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Nano Em1 0.6B v2, and what is it best at?›
#133 of 200 in Embeddings.
Is Nano Em1 0.6B v2 better than All MiniLM L12 v2?›
On MTEB English v2 · Retrieval · English, Nano Em1 0.6B v2 scores 43.2 vs 43.7 — about the same.
When was Nano Em1 0.6B v2 released? Is there a newer version?›
Released 2026-07-20. It is the current version in its line.
Is Nano Em1 0.6B v2 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Nano Em1 0.6B v2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Nano Em1 0.6B v2?›
Nano Em1 0.6B v2 is an open-weights embeddings & retrieval model from KiteFishAI, released Jul 2026.
What are the best alternatives to Nano Em1 0.6B v2?›
EmbeddingGemma 300M (better), Yuan Embedding 2.0 En (open weights).