Xiaobu Embedding v2 measured on 6 of 261 Embeddings benchmarks6
BenchmarkByScoreRank
Retrieval5
Reranking1
No benchmark matches
self-host onlyprice
90.4MTEB Medical v1
Jun 2024released
1K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
KBetterQZhou Embedding ZhOpen+11%——Memory (4-bit): 0.2 GB → 4.5 GBKBetterQZhou EmbeddingunstatedOpen+11%——Memory (4-bit): 0.2 GB → 4.2 GBTBetterConan Embedding v2unstated+8%——
BetterSeed1.5 Embeddingunstated+4%——
OpenYoutu Embeddingsame——Memory (4-bit): 0.2 GB → 1.6 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
KQZhou Embedding ZhOpen+11%——Memory (4-bit): 0.2 GB → 4.5 GBKQZhou EmbeddingunstatedOpen+11%——Memory (4-bit): 0.2 GB → 4.2 GBTConan Embedding v2unstated+8%——Seed1.5 Embeddingunstated+4%——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
Licencenot verified
History
2 versionsBenchmarks
in Embeddings & RetrievalFAQ
How much does Xiaobu Embedding v2 cost?›
There is no per-unit API price: self-host only.
Is Xiaobu Embedding v2 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Xiaobu Embedding v2, and what is it best at?›
#6 of 199 in Embeddings.
Is Xiaobu Embedding v2 better than Ritrieve Zh v1?›
On MTEB Mandarin Chinese v1 · Pair Classification · Mandarin Chinese, Xiaobu Embedding v2 scores 85.9 vs 86 — about the same.
When was Xiaobu Embedding v2 released? Is there a newer version?›
Released 2024-06-30. It is the current version in its line.
Is Xiaobu Embedding v2 open source?›
Yes, the weights are open (not specified licence).
Can I run Xiaobu Embedding v2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Xiaobu Embedding v2?›
Xiaobu Embedding v2 is an open-weights embeddings & retrieval model from lier007, released Jun 2024.
What are the best alternatives to Xiaobu Embedding v2?›
QZhou Embedding Zh (better).