ModBERTBr Matryoshka Sts Pt measured on 7 of 261 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
17.1MTEB Portuguese v1
Apr 2026released
768Dimensions
1K tokensMax input
ptLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+26%—$0.002Languages: not verified+1aOpenGiga Embeddings Instruct 3B 0826unstated×2——Memory (4-bit): 0.1 GB → 1.9 GBsBetterAll MiniLM L6 v2unstatedOpen+25%—$0.005Max input: 1K tokens → 0K tokenssBetterAll MiniLM L12 v2unstatedOpen+13%—$0.005Max input: 1K tokens → 0K tokens
BetterQwen 3 Embedding 0.6BunstatedOpen+32%—$0.01Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+26%—$0.002Languages: not verified+1sAll MiniLM L6 v2unstatedOpen+25%—$0.005Max input: 1K tokens → 0K tokenssAll MiniLM L12 v2unstatedOpen+13%—$0.005Max input: 1K tokens → 0K tokensQwen 3 Embedding 0.6BunstatedOpen+32%—$0.01Languages: not verified+1tGte LargeunstatedOpen+29%—$0.01Memory (4-bit): 0.1 GB → 0.2 GBModelScoreCostPriceWhat changes
aGiga Embeddings Instruct 3B 0826unstatedOpen×2——Memory (4-bit): 0.1 GB → 1.9 GBaGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+99%——Memory (4-bit): 0.1 GB → 6.3 GB
KaLM Embedding Gemma3 12B 2511Open+84%——Languages: not verified+1BBidirLM 1.7B EmbeddingOpen+70%——Memory (4-bit): 0.1 GB → 1 GB
Llama Embed Nemotron 8BOpen+70%——Languages: not verified+1Run 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
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does ModBERTBr Matryoshka Sts Pt cost?›
There is no per-unit API price: self-host only.
Is ModBERTBr Matryoshka Sts Pt free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is ModBERTBr Matryoshka Sts Pt, and what is it best at?›
#159 of 191 in Embeddings.
Is ModBERTBr Matryoshka Sts Pt better than Embedder 100p?›
On MTEB Portuguese v1 · Multilabel Classification · Portuguese, ModBERTBr Matryoshka Sts Pt scores 17.1 vs 17.1 — about the same.
When was ModBERTBr Matryoshka Sts Pt released? Is there a newer version?›
Released 2026-04-01. It is the current version in its line.
Is ModBERTBr Matryoshka Sts Pt open source?›
Yes, the weights are open (MIT licence).
Can I run ModBERTBr Matryoshka Sts Pt locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is ModBERTBr Matryoshka Sts Pt?›
ModBERTBr Matryoshka Sts Pt is an open-weights embeddings & retrieval model from iara-project, released Apr 2026.
What are the best alternatives to ModBERTBr Matryoshka Sts Pt?›
EmbeddingGemma 300M (better), Giga Embeddings Instruct 3B 0826 (open weights).