UltraBERT Embed 150M measured on 17 of 261 Embeddings benchmarks17
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
57.2MTEB English v2
Oct 2026released
768Dimensions
33K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →···
45Snowflake Arctic Embed M57.546UltraBERT Embed 150M57.247Snowflake Arctic Embed M Long57Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+21%—$0.01Languages: not verified+1IOpenYuan Embedding 2.0 Enunstated+24%——Memory (4-bit): 0.1 GB → 0.4 GBBetterQwen 3 Embedding 0.6BunstatedOpen+8%—$0.01Languages: not verified+1BetterQwen 3 Embedding 4BunstatedOpen+20%—$0.02Languages: not verified+1
BetterJina Embeddings v5 Text SmallunstatedOpen+5%—$0.05Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+21%—$0.01Languages: not verified+1Qwen 3 Embedding 0.6BunstatedOpen+8%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+20%—$0.02Languages: not verified+1Jina Embeddings v5 Text SmallunstatedOpen+5%—$0.05Languages: not verified+1
Gemini Embedding 001unstated+13%—$0.15Max input: 33K tokens → 2K tokens+1ModelScoreCostPriceWhat changes
IYuan Embedding 2.0 EnunstatedOpen+24%——Memory (4-bit): 0.1 GB → 0.4 GBQwen 3 Embedding 8BunstatedOpen+21%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+20%—$0.02Languages: not verified+1KQZhou EmbeddingunstatedOpen+17%——Memory (4-bit): 0.1 GB → 4.2 GBiJasper Token Compression 600MunstatedOpen+16%——Memory (4-bit): 0.1 GB → 0.4 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
Benchmarks
in Embeddings & RetrievalFAQ
How much does UltraBERT Embed 150M cost?›
There is no per-unit API price: self-host only.
Is UltraBERT Embed 150M free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is UltraBERT Embed 150M, and what is it best at?›
#43 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
Is UltraBERT Embed 150M better than Snowflake Arctic Embed M?›
On MTEB English v2 · Retrieval · English, UltraBERT Embed 150M scores 57.2 vs 57.5 — about the same.
When was UltraBERT Embed 150M released? Is there a newer version?›
Released 2026-10-10. It is the current version in its line.
Is UltraBERT Embed 150M open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run UltraBERT Embed 150M locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is UltraBERT Embed 150M?›
UltraBERT Embed 150M is an open-weights embeddings & retrieval model from dmis-lab, released Oct 2026.
What are the best alternatives to UltraBERT Embed 150M?›
Qwen 3 Embedding 8B (better), Yuan Embedding 2.0 En (open weights).