Ogma Small measured on 4 of 194 Embeddings benchmarks4
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
51.6MTEB Mandarin Chinese v1
Apr 2026released
1K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
sBetterAll Mpnet Base v2unstatedOpen+24%—$0.005Max input: 1K tokens → 0K tokens+1KOpenQZhou Embeddingunstated×2.3——Memory (4-bit): 0 GB → 4.2 GBsBetterAll MiniLM L12 v2unstatedOpen+23%—$0.005Max input: 1K tokens → 0K tokenssBetterAll MiniLM L6 v2unstatedOpen+23%—$0.005Max input: 1K tokens → 0K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
sAll Mpnet Base v2unstatedOpen+24%—$0.005Max input: 1K tokens → 0K tokens+1sAll MiniLM L12 v2unstatedOpen+23%—$0.005Max input: 1K tokens → 0K tokenssAll MiniLM L6 v2unstatedOpen+23%—$0.005Max input: 1K tokens → 0K tokensModelScoreCostPriceWhat changes
KQZhou EmbeddingunstatedOpen×2.3——Memory (4-bit): 0 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
LicenceCC BY-NC 4.0no commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Ogma Small cost?›
There is no per-unit API price: self-host only.
Is Ogma Small free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ogma Small, and what is it best at?›
#85 of 85 in Embeddings.
Is Ogma Small better than Ogma Micro?›
On MTEB Mandarin Chinese v1 · Classification · Mandarin Chinese, Ogma Small scores 34.9 vs 35.3 — about the same.
When was Ogma Small released? Is there a newer version?›
Released 2026-04-23. It is the current version in its line.
Is Ogma Small open source?›
Yes, the weights are open (cc-by-nc-4.0 licence).
Can I run Ogma Small locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Ogma Small?›
Ogma Small is an open-weights embeddings & retrieval model from axiotic, released Apr 2026.
What are the best alternatives to Ogma Small?›
All Mpnet Base v2 (better), QZhou Embedding (open weights).