Palyginti
ERNIE 4.5 0.3B vs ERNIE 4.5 VL 28B-A3B
Sudėkite du–keturis modelius greta pagal laukus, kurie lemia diegimą: kontekstas, kaina, regionas, licencija, kalbos, talpinimas ir tai, kas patikrinta.
| ERNIE 4.5 0.3B | ERNIE 4.5 VL 28B-A3B | |
|---|---|---|
| Teikėjas | Baidu | Baidu |
| Parametrai | 0.4B | 29.4B |
| Konteksto langas | Nepatvirtinta: teikėjas nepagrindė šio teiginio. | Nepatvirtinta: teikėjas nepagrindė šio teiginio. |
| Licencija | apache-2.0 | apache-2.0 |
| Modalumai | text | text, vision |
| Išleidimo data | 2025-06-28 | 2025-06-28 |
| Kalbos | Stipri: en Pakankama: zh | Stipri: en Pakankama: zh |
| Atvirieji svoriai | taip | taip |
| Užduotys | Maža kaina, Daugiakalbis palaikymas | Vizija, Mąstymas |
Kai du modeliai skiriasi, ši lentelė parodo skirtumą ir sustoja. LLM EU neskelbia nugalėtojo ženklo be dokumentuoto tos užduoties balo, o trūkstamas skaičius lieka trūkstamas, o ne tampa nuliu.
Kada naudoti
ERNIE 4.5 0.3B
Stiprybės
- 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 0.4B parameters it fits on a single accelerator
- the model page lists en
Apribojimai
- 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 0.4B parameters, the weights fit on a single modest accelerator
- a base checkpoint: it answers nothing useful without fine-tuning or a task head
Užduotys
ERNIE 4.5 VL 28B-A3B
Stiprybės
- 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
- the model page lists en
Apribojimai
- 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 29.4B parameters, self-hosting needs a single accelerator with enough memory for the weights
- a base checkpoint: it answers nothing useful without fine-tuning or a task head
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model
Užduotys
Užduotys: Nepatvirtinta: teikėjas nepagrindė šio teiginio.