QZhou Embedding measured on 17 of 194 Embeddings benchmarks17
BenchmarkByScoreRank
Retrieval8
Other9
No benchmark matches
self-host onlyprice
67.1MTEB English v2
Aug 2025released
3,584Dimensions
33K tokensMax input
en, zhLanguages
Rankingconfiguration unstated?
Full ranking →···
12Giga Embeddings Instruct 3B 082648.813QZhou Embedding48.814Stella En 400M v548.3Strong at
Alternatives?
ModelScoreCostPriceWhat changes
cBetterF2LLM 4BunstatedOpen+46%——Languages: loses zhcBetterF2LLM 1.7BunstatedOpen+24%——Languages: loses zhcBetterF2LLM v2 14BunstatedOpen+18%——Memory (4-bit): 4.2 GB → 8.4 GBcBetterF2LLM v2 8BunstatedOpen+15%——Memory (4-bit): 4.2 GB → 4.5 GBcBetterF2LLM v2 4BunstatedOpen+14%——ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
cF2LLM 4BunstatedOpen+46%——Languages: loses zhcF2LLM 1.7BunstatedOpen+24%——Languages: loses zhcF2LLM v2 14BunstatedOpen+18%——Memory (4-bit): 4.2 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+15%——Memory (4-bit): 4.2 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+14%——ModelScoreCostPriceWhat changes
cF2LLM 4BunstatedOpen+46%——Languages: loses zhcF2LLM 1.7BunstatedOpen+24%——Languages: loses zhcF2LLM v2 14BunstatedOpen+18%——Memory (4-bit): 4.2 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+15%——Memory (4-bit): 4.2 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+14%——ModelScoreCostPriceWhat changes
KQZhou Embedding ZhOpenn/a——Max input: 33K tokens → 8K tokens+2All Kingsoft-LLM models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 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 QZhou Embedding cost?›
There is no per-unit API price: self-host only.
Is QZhou Embedding free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is QZhou Embedding, and what is it best at?›
#7 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
Is QZhou Embedding better than Giga Embeddings Instruct 3B 0826?›
On MTEB Medical v1 · Clustering · English, QZhou Embedding scores 48.8 vs 48.8 — about the same.
When was QZhou Embedding released? Is there a newer version?›
Released 2025-08-24. It is the current version in its line.
Is QZhou Embedding open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run QZhou Embedding locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is QZhou Embedding?›
QZhou Embedding is an open-weights embeddings & retrieval model from Kingsoft-LLM, released Aug 2025.
What are the best alternatives to QZhou Embedding?›
F2LLM 4B (better).