Siglip So400m Patch16 256 I18n measured on 3 of 195 Multimodal benchmarks3
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
44MIEB lite
Jan 2024released
1,152Dimensions
0K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
LLCO Embedding Omni 7BunstatedOpen+87%——Memory (4-bit): 0.7 GB → 5.4 GBLLCO Embedding Omni 3BunstatedOpen+81%——Memory (4-bit): 0.7 GB → 2.8 GBHE5 Omni 7BunstatedOpen+76%——Memory (4-bit): 0.7 GB → 5.4 GBModelScoreCostPriceWhat changes
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 Siglip So400m Patch16 256 I18n cost?›
There is no per-unit API price: self-host only.
Is Siglip So400m Patch16 256 I18n free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Siglip So400m Patch16 256 I18n, and what is it best at?›
#13 of 56 in Multimodal.
Is Siglip So400m Patch16 256 I18n better than BidirLM Omni 2.5B Embedding?›
On MIEB lite · Visual semantic similarity (multilingual) · multilingual (13 languages), Siglip So400m Patch16 256 I18n scores 44 vs 45.7 — lower.
When was Siglip So400m Patch16 256 I18n released? Is there a newer version?›
Released 2024-01-08. It is the current version in its line.
Is Siglip So400m Patch16 256 I18n open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Siglip So400m Patch16 256 I18n locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Siglip So400m Patch16 256 I18n?›
Siglip So400m Patch16 256 I18n is an open-weights embeddings & retrieval model from Google, released Jan 2024.
What are the best alternatives to Siglip So400m Patch16 256 I18n?›
EmbeddingGemma 2 (better), LCO Embedding Omni 7B (open weights).