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 |
OpenGVLab
|
|---|---|
| Company | OpenGVLab |
| Release Date | 2025-04-11 |
| Parameters (B) | 78.4 |
| Architecture | ViT-MLP-LLM |
| Context Window | 32768 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 152 |
| Compute | Minimum 2x NVIDIA A100/H100 80GB GPUs for 8-bit inference; 3x 80GB GPUs recommended for bf16 |
| Benchmark: BBH | 85.2 |
| Benchmark: C-Eval | 89.5 |
| Benchmark: GSM8K | 90.5 |
| Benchmark: HellaSwag | 95.6 |
| Benchmark: HumanEval | 82.3 |
| Benchmark: MATH | 78.9 |
| Benchmark: MBPP | 76.7 |
| Benchmark: MMLU | 86.9 |
| Benchmark: MMMU | 72.2 |
| Pricing (Input) | — |
| Pricing (Output) | — |