Usporedi
Intern-S1 Mini vs Intern-S1
Stavite dva do četiri modela jedan pored drugoga na poljima koja odlučuju o implementaciji: kontekst, cijena, regija, licenca, jezici, hosting i što je verificirano.
| Intern-S1 Mini | Intern-S1 | |
|---|---|---|
| Pružatelj | Shanghai AI Laboratory | Shanghai AI Laboratory |
| Parametri | 8.5B | 240.7B |
| Prozor konteksta | Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. | Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. |
| Licenca | apache-2.0 | apache-2.0 |
| Modaliteti | text, vision | text, vision |
| Datum izdanja | 18. kol 2025. | 24. srp 2025. |
| Jezici | Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. | Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. |
| Otvoreni utezi | da | da |
| Zadaci | Zaključivanje, Vizija, Niska cijena | Zaključivanje, Vizija |
Kada se dva modela razlikuju, ova tablica pokazuje razliku i tu staje. LLM EU ne objavljuje značku pobjednika bez dokumentiranog rezultata za taj zadatak, a brojka koja nedostaje ostaje nedostajuća umjesto da postane nula.
Kada ga koristiti
Intern-S1 Mini
Prednosti
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- Apache-2.0 licence, so commercial self-hosting is permitted without a separate agreement
- at 8.5B parameters it fits on a single accelerator
Ograničenja
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 8.5B parameters, the weights fit on a single modest accelerator
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model
Zadaci
Intern-S1
Prednosti
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- Apache-2.0 licence, so commercial self-hosting is permitted without a separate agreement
Ograničenja
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 240.7B parameters, self-hosting needs multiple high-memory accelerators
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model
Zadaci
Zadaci: Zaključivanje, Vizija