Sammenlign
Gemma 3 1B It vs Gemma 3 12B It
Sæt to til fire modeller side om side på de felter, der afgør en udrulning: kontekst, pris, region, licens, sprog, hosting og hvad der er verificeret.
| Gemma 3 1B It | Gemma 3 12B It | |
|---|---|---|
| Udbyder | Google DeepMind | Google DeepMind |
| Parametre | 1B | 12.2B |
| Kontekstvindue | Ikke verificeret: udbyderen har ikke dokumenteret denne påstand. | Ikke verificeret: udbyderen har ikke dokumenteret denne påstand. |
| Licens | gemma | gemma |
| Modaliteter | text | text, vision |
| Udgivelsesdato | 10. mar. 2025 | 01. mar. 2025 |
| Sprog | Ikke verificeret: udbyderen har ikke dokumenteret denne påstand. | Ikke verificeret: udbyderen har ikke dokumenteret denne påstand. |
| Åbne vægte | ja | ja |
| Opgaver | Flersproget support, Lav pris | Flersproget support, Vision, Resumé |
Hvor to modeller adskiller sig, viser denne tabel forskellen og stopper. LLM EU offentliggør ikke et vinderbadge uden en dokumenteret score for den opgave, og et manglende tal forbliver manglende i stedet for at blive et nul.
Hvornår man bruger den
Gemma 3 1B It
Styrker
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- at 1B parameters it fits on a single accelerator
- instruction-tuned checkpoint with a chat template in the repository
Begrænsninger
- 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 1B parameters, the weights fit on a single modest accelerator
Opgaver
Gemma 3 12B It
Styrker
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- instruction-tuned checkpoint with a chat template in the repository
Begrænsninger
- 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 12.2B parameters, self-hosting needs a single accelerator with enough memory for the weights
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model
Opgaver
Opgaver: Flersproget support