Loading…
Loading…
Models / Qwen2-VL
3 models (2B to 72B) · ↓ 3.5M downloads a month · from $0.10/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| InstructQwen/Qwen2-VL-2B-Instruct | vLLM | 4.4 GB | 7.4 GB | $0.10/h RTX 3060 |
| Instruct AWQQwen/Qwen2-VL-2B-Instruct-AWQ | vLLM | 3.0 GB | 5.8 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Instruct AWQQwen/Qwen2-VL-7B-Instruct-AWQ | vLLM | 6.9 GB | 10.4 GB | $0.10/h RTX 3060 |
| InstructQwen/Qwen2-VL-7B-Instruct | vLLM | 17 GB | 21.2 GB | $0.18/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| InstructQwen/Qwen2-VL-72B-Instruct | vLLM | 147 GB | 168.3 GB | $1.38/h 8x RTX 3090 |
| QVQ 72B PreviewQwen/QVQ-72B-Preview | vLLM | 147 GB | 168.3 GB | $1.38/h 8x RTX 3090 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").