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 | 2025-08-25 |
| Parameters (B) | 2.4 |
| Architecture | ViT-MLP-LLM |
| Context Window | 32768 |
| Input Modalities | text, image, video |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 8 |
| Compute | Single NVIDIA GPU with 8GB+ VRAM for BF16 inference; supports consumer cards (e.g., RTX 3060) or data-center GPUs (A100). Flash attention recommended. |
| Benchmark: AIME-2024 | 40 |
| Benchmark: AIME-2025 | 23.3 |
| Benchmark: BBH | 62.3 |
| Benchmark: C-Eval | 61 |
| Benchmark: GSM8K | 77.2 |
| Benchmark: HellaSwag | 74.4 |
| Benchmark: HumanEval | 65.9 |
| Benchmark: MATH | 85.5 |
| Benchmark: MMLU | 61.9 |
| Benchmark: MMMU | 53 |
| Pricing (Input) | — |
| Pricing (Output) | — |