Loading…
Loading…
Models / JoyAI-VL-Interaction
GPU memory needed (smallest version of each): JoyAI-VL-Interaction ~8.77B about 13.3 GB. The cheapest runs on 2x RTX 3060 from $0.16/h right now.
4 models (~8.77B to ~8.77B) · ↓ 1.2K downloads a month · from $0.16/h on 2x 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 |
|---|---|---|---|---|
| Originaljdopensource/JoyAI-VL-Interaction | vLLM | 18 GB | 24.4 GB | $0.44/h RTX 5000 Ada |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaljdopensource/JoyAI-VL-Interaction-INT4 | vLLM | 7.5 GB | 13.3 GB | $0.16/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaljdopensource/JoyAI-VL-Interaction-INT8 | vLLM | 11 GB | 16.7 GB | $0.16/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaljdopensource/JoyAI-VL-Interaction-FP8 | vLLM | 11 GB | 16.7 GB | $0.16/h 2x RTX 3060 |
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").