Nano Em1 0.6B v2.1 measured on 8 of 194 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
46.6MTEB English v2
Aug 2026released
1,024Dimensions
8K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →···
33Tarka Embedding 350M v155.734Nano Em1 0.6B v2.155.435Giga Embeddings Instruct 480M 082655.2Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+6%—$0.01Languages: not verified+1cOpenF2LLM 4Bunstated+24%——Memory (4-bit): 0.4 GB → 2.4 GBBetterQwen 3 Embedding 4BunstatedOpen+4%—$0.02Languages: not verified+1
BetterGemini Embedding 001unstated+7%—$0.15Max input: 8K tokens → 2K tokenscBetterF2LLM 1.7BunstatedOpen+16%——Memory (4-bit): 0.4 GB → 1 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+6%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+4%—$0.02Languages: not verified+1Gemini Embedding 001unstated+7%—$0.15Max input: 8K tokens → 2K tokenscF2LLM 4BunstatedOpen+24%——Memory (4-bit): 0.4 GB → 2.4 GBcF2LLM 1.7BunstatedOpen+16%——Memory (4-bit): 0.4 GB → 1 GBModelScoreCostPriceWhat changes
cF2LLM 4BunstatedOpen+24%——Memory (4-bit): 0.4 GB → 2.4 GBcF2LLM 1.7BunstatedOpen+16%——Memory (4-bit): 0.4 GB → 1 GBcF2LLM v2 8BunstatedOpen+13%——Memory (4-bit): 0.4 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+12%——Memory (4-bit): 0.4 GB → 2.4 GBKQZhou EmbeddingunstatedOpen+11%——Memory (4-bit): 0.4 GB → 4.2 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
History
2 versionsBenchmarks
in Embeddings & RetrievalFAQ
How much does Nano Em1 0.6B v2.1 cost?›
There is no per-unit API price: self-host only.
Is Nano Em1 0.6B v2.1 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 v2.1, and what is it best at?›
#123 of 200 in Embeddings.
Is Nano Em1 0.6B v2.1 better than Tarka Embedding 350M v1?›
On MTEB English v2 · Clustering · English, Nano Em1 0.6B v2.1 scores 55.4 vs 55.7 — about the same.
When was Nano Em1 0.6B v2.1 released? Is there a newer version?›
Released 2026-08-11. It is the current version in its line.
Is Nano Em1 0.6B v2.1 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Nano Em1 0.6B v2.1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Nano Em1 0.6B v2.1?›
Nano Em1 0.6B v2.1 is an open-weights embeddings & retrieval model from KiteFishAI, released Aug 2026.
What are the best alternatives to Nano Em1 0.6B v2.1?›
Qwen 3 Embedding 8B (better), F2LLM 4B (open weights).