mSlideOn measured on 10 of 194 Embeddings benchmarks10
BenchmarkByScoreRank
Retrieval1
Other9
No benchmark matches
price not verifiedprice
56BEIR
—released
8K tokensMax input
en, es, fr +7Languages
Alternatives?
ModelScoreCostPriceWhat changes
Betterpplx Embed v1 0.6BOpen+8%—$0.004Languages: not verified+1
OpenKaLM Embedding Gemma3 12B 2511+25%——Languages: not verified+1
BetterQwen 3 Embedding 8BunstatedOpen+17%—$0.01Languages: not verified+1BetterQwen 3 Embedding 0.6BunstatedOpen+7%—$0.01Languages: not verified+1BetterQwen 3 Embedding 4BunstatedOpen+15%—$0.02Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
pplx Embed v1 0.6BOpen+8%—$0.004Languages: not verified+1Qwen 3 Embedding 8BunstatedOpen+17%—$0.01Languages: not verified+1Qwen 3 Embedding 0.6BunstatedOpen+7%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+15%—$0.02Languages: not verified+1
Jina Embeddings v5 Text NanounstatedOpen+4%—$0.02Languages: not verifiedModelScoreCostPriceWhat changes
KaLM Embedding Gemma3 12B 2511Open+25%——Languages: not verified+1OOcten Embedding 8BOpen+18%——Languages: loses es, fr, de +6+1GGeevec Embeddings 1.0 LiteunstatedOpen+17%——Languages: not verifiedQwen 3 Embedding 8BunstatedOpen+17%—$0.01Languages: not verified+1
Harrier OSS v1 0.6BunstatedOpen+17%——Memory (4-bit): 0.2 GB → 0.4 GBModelScoreCostPriceWhat changes
lmDenseOnOpenn/a——Languages: loses sv, no, codelmLateOnOpenn/a——Languages: loses sv, no, codelDenseOnOpenn/a——Max input: 8K tokens → 1K tokens+1lDenseOn UnsupervisedOpenn/a——Max input: 8K tokens → 1K tokens+1lLateOnOpenn/a——Max input: 8K tokens → 0K tokens+1lColBERT ZeroOpenn/a——Max input: 8K tokens → 1K tokens+1lColBERT Zero SupervisedOpenn/a——Max input: 8K tokens → 1K tokens+1lColBERT Zero UnsupervisedOpenn/a——Max input: 8K tokens → 0K tokens+1All lightonai models →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
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does mSlideOn cost?›
There is no per-unit API price: price not verified.
How good is mSlideOn, and what is it best at?›
#34 of 196 in Embeddings.
Is mSlideOn better than Gte Qwen2 1.5B Instruct?›
On MTEB multilingual v2 · Retrieval · multilingual (120 languages), mSlideOn scores 60.6 vs 60.8 — about the same.
Is mSlideOn open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run mSlideOn locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is mSlideOn?›
mSlideOn is an open-weights embeddings & retrieval model from lightonai.
What are the best alternatives to mSlideOn?›
pplx Embed v1 0.6B (better), KaLM Embedding Gemma3 12B 2511 (open weights).