Porovnať
ERNIE 4.5 21B-A3B Thinking vs ERNIE 4.5 VL 28B-A3B
Postavte dva až štyri modely vedľa seba podľa polí, ktoré rozhodujú o nasadení: kontext, cena, región, licencia, jazyky, hosťovanie a čo je overené.
| ERNIE 4.5 21B-A3B Thinking | ERNIE 4.5 VL 28B-A3B | |
|---|---|---|
| Poskytovateľ | Baidu | Baidu |
| Parametre | 21.8B | 29.4B |
| Kontextové okno | Neoverené: poskytovateľ tento údaj nedokumentoval. | Neoverené: poskytovateľ tento údaj nedokumentoval. |
| Licencia | apache-2.0 | apache-2.0 |
| Modalitá | text | text, vision |
| Dátum vydania | 08. 9. 2025 | 28. 6. 2025 |
| Jazyky | Silná: en Dostatočná: zh | Silná: en Dostatočná: zh |
| Otvorené váhy | áno | áno |
| Úlohy | Uvažovanie, Nízke náklady | Videnie, Uvažovanie |
Ak sa dva modely líšia, táto tabuľka zobrazí rozdiel a skončí. LLM EU nezverejňuje odznak víťaza bez zdokumentovaného skóre pre danú úlohu a chýbajúci údaj zostáva chýbajúci, namiesto toho, aby sa stal nulou.
Kedy ho použiť
ERNIE 4.5 21B-A3B Thinking
Silné stránky
- 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
- instruction-tuned checkpoint with a chat template in the repository
Obmedzenia
- 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 21.8B parameters, self-hosting needs a single accelerator with enough memory for the weights
Úlohy
ERNIE 4.5 VL 28B-A3B
Silné stránky
- 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
Obmedzenia
- 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
Úlohy
Úlohy: Uvažovanie
Porovnať modely
Porovnať modely →- DeepSeek Coder V2 Lite Instruct vs ERNIE 4.5 21B-A3B Thinking
- DeepSeek R1 Distill Qwen 14B vs ERNIE 4.5 21B-A3B Thinking
- DeepSeek-R1-Distill-Qwen-32B vs ERNIE 4.5 21B-A3B Thinking
- DeepSeek V2 Lite vs ERNIE 4.5 21B-A3B Thinking
- Devstral Small 2 (24B) vs ERNIE 4.5 21B-A3B Thinking
- Diffusiongemma 26B A4B It vs ERNIE 4.5 VL 28B-A3B