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 |
meta-llama
|
|---|---|
| Company | meta-llama |
| Release Date | 2024-09-25 |
| Parameters (B) | 11 |
| Architecture | Multimodal Transformer |
| Context Window | 128000 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | llama3.2 |
| Score | 3 |
| VRAM (GB) | 24 |
| Compute | Single NVIDIA GPU with 24GB+ VRAM (e.g. RTX 3090, A5000) for BF16 inference; 8GB+ with INT4 quantization |
| Benchmark: GPQA | 32.8 |
| Benchmark: MATH | 51.9 |
| Benchmark: MMLU | 73 |
| Benchmark: MMMU | 50.7 |
| Benchmark: MMMU-Pro | 33 |
| Pricing (Input) | — |
| Pricing (Output) | — |