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) | 8 |
| Architecture | ViT-MLP-LLM |
| Context Window | 32768 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 24 |
| Compute | Single NVIDIA GPU with ≥24GB VRAM (e.g. RTX 4090, A10, L4) for BF16 inference; ~17GB for model weights, ~10GB with 8-bit quantization |
| Benchmark: BBH | 77.4 |
| Benchmark: C-Eval | 84.5 |
| Benchmark: GSM8K | 83.1 |
| Benchmark: HellaSwag | 90.2 |
| Benchmark: HumanEval | 78.1 |
| Benchmark: MATH | 72.2 |
| Benchmark: MBPP | 69.3 |
| Benchmark: MMLU | 77.3 |
| Benchmark: MMMU | 62.7 |
| Pricing (Input) | — |
| Pricing (Output) | — |