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) | 15.1 |
| Architecture | ViT-MLP-LLM |
| Context Window | 32768 |
| Input Modalities | text, image, video |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 31 |
| Compute | Single NVIDIA A100 40GB for BF16 inference (~31 GB VRAM); 4-bit/8-bit quantization fits 24 GB consumer GPUs |
| Benchmark: BBH | 85.4 |
| Benchmark: C-Eval | 88.1 |
| Benchmark: GSM8K | 89.7 |
| Benchmark: HellaSwag | 92.7 |
| Benchmark: HumanEval | 87.2 |
| Benchmark: MATH | 81.4 |
| Benchmark: MBPP | 86.8 |
| Benchmark: MMLU | 84.4 |
| Benchmark: MMMU | 67.1 |
| Pricing (Input) | — |
| Pricing (Output) | — |