Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
google
|
|---|---|
| Company | |
| Release Date | 2024-05-14 |
| Parameters (B) | 3 |
| Architecture | Transformer |
| Context Window | 128 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | gemma |
| Score | 0 |
| VRAM (GB) | 8 |
| Compute | Single NVIDIA GPU with ~8GB VRAM for bfloat16/float16 inference (~12GB+ for float32); supports 4-bit/8-bit quantization via bitsandbytes; trained on Google TPUv5e |
| Pricing (Input) | — |
| Pricing (Output) | — |