Qwen 3 Embedding Scandi 0.6B measured on 8 of 261 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
55.2MTEB Scandinavian v1
Oct 2025released
1,024Dimensions
33K tokensMax input
Danish, Norwegian, SwedishLanguages
Alternatives?
ModelScoreCostPriceWhat changes
iBetterMultilingual E5 LargeunstatedOpen+40%—$0.01Max input: 33K tokens → 1K tokens+1cOpenF2LLM v2 8Bunstated+61%——Memory (4-bit): 0.2 GB → 4.5 GB
BetterBge M3unstatedOpen+39%—$0.01Max input: 33K tokens → 8K tokens+2iBetterMultilingual E5 Large InstructunstatedOpen+39%—$0.01Max input: 33K tokens → 1K tokens+1
BetterQwen 3 Embedding 0.6BunstatedOpen+34%—$0.01Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
iMultilingual E5 LargeunstatedOpen+40%—$0.01Max input: 33K tokens → 1K tokens+1Bge M3unstatedOpen+39%—$0.01Max input: 33K tokens → 8K tokens+2iMultilingual E5 Large InstructunstatedOpen+39%—$0.01Max input: 33K tokens → 1K tokens+1Qwen 3 Embedding 0.6BunstatedOpen+34%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+49%—$0.02Languages: not verified+1ModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen+61%——Memory (4-bit): 0.2 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+58%——Memory (4-bit): 0.2 GB → 2.4 GBnSaga Embed v1Open+57%——Max input: 33K tokens → 1K tokens+1iInf Retriever v1unstatedOpen+54%——Languages: loses Danish, Norwegian, Swedish+1cF2LLM v2 1.7BunstatedOpen+54%——Memory (4-bit): 0.2 GB → 1 GBModelScoreCostPriceWhat changes
eEmbeddingGemma Scandi 300MOpen+18%——Max input: 33K tokens → 2K tokensAll emillykkejensen 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
Benchmarks
in Embeddings & RetrievalFAQ
How much does Qwen 3 Embedding Scandi 0.6B cost?›
There is no per-unit API price: self-host only.
Is Qwen 3 Embedding Scandi 0.6B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Qwen 3 Embedding Scandi 0.6B, and what is it best at?›
#158 of 205 in Embeddings.
Is Qwen 3 Embedding Scandi 0.6B better than Nb Sbert Base?›
On MTEB Scandinavian v1 · Retrieval · multilingual (3 languages), Qwen 3 Embedding Scandi 0.6B scores 46 vs 48.3 — lower.
When was Qwen 3 Embedding Scandi 0.6B released? Is there a newer version?›
Released 2025-10-17. It is the current version in its line.
Is Qwen 3 Embedding Scandi 0.6B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen 3 Embedding Scandi 0.6B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Qwen 3 Embedding Scandi 0.6B?›
Qwen 3 Embedding Scandi 0.6B is an open-weights embeddings & retrieval model from emillykkejensen, released Oct 2025.
What are the best alternatives to Qwen 3 Embedding Scandi 0.6B?›
Multilingual E5 Large (better), F2LLM v2 8B (open weights).