Qabbel
Intern-S1 Mini vs Intern-S1
Qiegħed żewġ mudelli sa erbgħa ma' xulxin fuq l-oqsma li jiddeċiedu deployment: kuntest, prezz, reġjun, liċenzja, lingwi, hosting, u x'hu verifikat.
| Intern-S1 Mini | Intern-S1 | |
|---|---|---|
| Fornitur | Shanghai AI Laboratory | Shanghai AI Laboratory |
| Parametri | 8.5B | 240.7B |
| Tieqa tal-kuntest | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. |
| Liċenzja | apache-2.0 | apache-2.0 |
| Modalitajiet | text, vision | text, vision |
| Data tar-rilaxx | 18 Aww 2025 | 24 Lul 2025 |
| Lingwi | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. |
| Piżijiet miftuħa | iva | iva |
| Kompiti | Raġunament, Viżjoni, Spiża baxxa | Raġunament, Viżjoni |
Fejn żewġ mudelli jvarjaw, din it-tabella turi d-differenza u tieqaf. LLM EU ma tippubblikax badge ta' rebbieħ mingħajr punteġġ dokumentat għal dik il-kompitu, u figura nieqsa tibqa' nieqsa minflok ma ssir żero.
Meta tużah
Intern-S1 Mini
Saħħiet
- 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
Limiti
- 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
Kompiti
Intern-S1
Saħħiet
- 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
Limiti
- 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
Kompiti
Kompiti: Raġunament, Viżjoni