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 |
| Parameters (B) | 1.1 |
| Architecture | ViT-MLP-LLM (InternViT-300M + Qwen3 Transformer) |
| Context Window | 32768 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 6 |
| Compute | Single GPU with 6GB+ VRAM (e.g. NVIDIA RTX 3060); supports BF16 and 8-bit quantization via Transformers |
| Benchmark: AIME-2024 | 13.7 |
| Benchmark: AIME-2025 | 14.7 |
| Benchmark: BBH | 46.8 |
| Benchmark: C-Eval | 49 |
| Benchmark: GSM8K | 62.8 |
| Benchmark: HellaSwag | 49.5 |
| Benchmark: HumanEval | 45.7 |
| Benchmark: MATH | 68.2 |
| Benchmark: MMLU | 49.1 |
| Benchmark: MMMU | 44.2 |
| Pricing (Input) | — |
| Pricing (Output) | — |