Instantly run open-source Vision-Language Models (VLMs). Each model includes a self-contained uv environment.
This table lists the VLMs currently included in this collection. Contributions are welcome!
| Model Name | Directory Name | Huggingface | Paper | GitHub |
|---|---|---|---|---|
| Qwen2.5-VL | qwen-2_5-vl | Link | Link | |
| Qwen3-VL | Link | Link | ||
| InternVL3 | internvl3 | Link | Link | Link |
| InternVL3.5 | internvl3_5 | Link | Link | Link |
| Heron-NVILA | heron-nvila | Link | ||
| Aya Vision | aya-vision | Link | Link | |
| Sarashina2-Vision | sarashina2-vision | Link |
Instantly run open-source Vision-Language Models (VLMs). Each model includes a self-contained uv environment.
This table lists the VLMs currently included in this collection. Contributions are welcome!
| Model Name | Directory Name | Huggingface | Paper | GitHub |
|---|---|---|---|---|
| Qwen2.5-VL | qwen-2_5-vl | Link | Link | |
| Qwen3-VL | Link | Link | ||
| InternVL3 | internvl3 | Link | Link | Link |
| InternVL3.5 | internvl3_5 | Link | Link | Link |
| Heron-NVILA | heron-nvila | Link | ||
| Aya Vision | aya-vision | Link | Link | |
| Sarashina2-Vision | sarashina2-vision | Link |
