Qabbel
Gemma 3 4B It vs Gemma 3 27B It
Qiegħed żewġ mudelli sa erbgħa ma' xulxin fuq l-oqsma li jiddeċiedu deployment: kuntest, prezz, reġjun, liċenzja, lingwi, hosting, u x'hu verifikat.
| Gemma 3 4B It | Gemma 3 27B It | |
|---|---|---|
| Fornitur | Google DeepMind | Google DeepMind |
| Parametri | 4.3B | 27.4B |
| Tieqa tal-kuntest | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. |
| Liċenzja | gemma | gemma |
| Modalitajiet | text, vision | text, vision |
| Data tar-rilaxx | 20 Fra 2025 | 01 Mar 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 | Appoġġ multilingwi, Viżjoni, Spiża baxxa | Appoġġ multilingwi, Viżjoni, Raġunament |
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
Gemma 3 4B It
Saħħiet
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- at 4.3B parameters it fits on a single accelerator
- instruction-tuned checkpoint with a chat template in the repository
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 4.3B 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
Gemma 3 27B It
Saħħiet
- 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
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 27.4B 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
Kompiti
Kompiti: Appoġġ multilingwi, Viżjoni