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 |
tiiuae
|
|---|---|
| Company | tiiuae |
| Release Date | 2024-05-21 |
| Parameters (B) | 11 |
| Architecture | LLaVA-NeXT vision-language model (CLIP ViT-L/14 encoder + Falcon causal decoder) |
| Context Window | 8192 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | unknown |
| Score | 0 |
| VRAM (GB) | 24 |
| Compute | Single NVIDIA GPU with 24GB+ VRAM (bf16 inference; A100 40GB or larger recommended) |
| Pricing (Input) | — |
| Pricing (Output) | — |