Miniac Embed measured on 8 of 261 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
45MTEB English v2
Feb 2026released
384Dimensions
1K tokensMax input
Rankingconfiguration unstated?
Full ranking →···
60F2LLM v2 330M82.861Miniac Embed82.862Voyage Large 2 Instruct82.8Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+7%—$0.01Memory (4-bit): 0 GB → 4.5 GBKOpenQZhou Embeddingunstated+11%——Memory (4-bit): 0 GB → 4.2 GBBetterQwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Memory (4-bit): 0 GB → 0.4 GBBetterQwen 3 Embedding 4BunstatedOpen+7%—$0.02Memory (4-bit): 0 GB → 2.4 GB
BetterJina Embeddings v5 Text NanounstatedOpen+7%—$0.02Memory (4-bit): 0 GB → 0.1 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+7%—$0.01Memory (4-bit): 0 GB → 4.5 GBQwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Memory (4-bit): 0 GB → 0.4 GBQwen 3 Embedding 4BunstatedOpen+7%—$0.02Memory (4-bit): 0 GB → 2.4 GBJina Embeddings v5 Text NanounstatedOpen+7%—$0.02Memory (4-bit): 0 GB → 0.1 GB
Text Embedding 005unstated+3%—$0.025ModelScoreCostPriceWhat changes
KQZhou EmbeddingunstatedOpen+11%——Memory (4-bit): 0 GB → 4.2 GBiJasper Token Compression 600MunstatedOpen+7%——Memory (4-bit): 0 GB → 0.4 GBQwen 3 Embedding 4BunstatedOpen+7%—$0.02Memory (4-bit): 0 GB → 2.4 GBQwen 3 Embedding 8BunstatedOpen+7%—$0.01Memory (4-bit): 0 GB → 4.5 GBJina Embeddings v5 Text NanounstatedOpen+7%—$0.02Memory (4-bit): 0 GB → 0.1 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 Miniac Embed cost?›
There is no per-unit API price: price not verified.
How good is Miniac Embed, and what is it best at?›
#129 of 200 in Embeddings.
Is Miniac Embed better than F2LLM v2 330M?›
On MTEB English v2 · STS · English, Miniac Embed scores 82.8 vs 82.8 — about the same.
When was Miniac Embed released? Is there a newer version?›
Released 2026-02-19. It is the current version in its line.
Is Miniac Embed open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Miniac Embed locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Miniac Embed?›
Miniac Embed is an open-weights embeddings & retrieval model from ManiacLabs, released Feb 2026.
What are the best alternatives to Miniac Embed?›
Qwen 3 Embedding 8B (better), QZhou Embedding (open weights).