FRIDA measured on 9 of 194 Embeddings benchmarks9
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
66.5MTEB Russian v1.1
Dec 2024released
1K tokensMax input
en, ruLanguages
Alternatives?
ModelScoreCostPriceWhat changes
aBetterGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+15%——Memory (4-bit): 0.5 GB → 6.3 GBaBetterGiga Embeddings Instruct 3B 0826unstatedOpen+10%——Memory (4-bit): 0.5 GB → 1.9 GBaBetterGiga Embeddings InstructunstatedOpen+9%——Memory (4-bit): 0.5 GB → 1.9 GBsBetterBERTAOpen+8%——aBetterGiga Embeddings Instruct 480M 0826unstatedOpen+5%——ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
aGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+15%——Memory (4-bit): 0.5 GB → 6.3 GBaGiga Embeddings Instruct 3B 0826unstatedOpen+10%——Memory (4-bit): 0.5 GB → 1.9 GBaGiga Embeddings InstructunstatedOpen+9%——Memory (4-bit): 0.5 GB → 1.9 GBsBERTAOpen+8%——aGiga Embeddings Instruct 480M 0826unstatedOpen+5%——ModelScoreCostPriceWhat changes
aGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+15%——Memory (4-bit): 0.5 GB → 6.3 GBaGiga Embeddings Instruct 3B 0826unstatedOpen+10%——Memory (4-bit): 0.5 GB → 1.9 GBaGiga Embeddings InstructunstatedOpen+9%——Memory (4-bit): 0.5 GB → 1.9 GBsBERTAOpen+8%——aGiga Embeddings Instruct 480M 0826unstatedOpen+5%——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
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does FRIDA cost?›
There is no per-unit API price: price not verified.
How good is FRIDA, and what is it best at?›
#11 of 194 in Embeddings.
Is FRIDA better than Giga Embeddings Instruct 480M 0826?›
On MTEB Russian v1.1 · Multilabel Classification · Russian, FRIDA scores 52.2 vs 54.8 — lower.
When was FRIDA released? Is there a newer version?›
Released 2024-12-29. It is the current version in its line.
Is FRIDA open source?›
Yes, the weights are open (MIT licence).
Can I run FRIDA locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is FRIDA?›
FRIDA is an open-weights embeddings & retrieval model from ai-forever, released Dec 2024.
What are the best alternatives to FRIDA?›
Giga Embeddings Instruct 10B A1.8B 0826 (better).