Loading…
Loading…
Models / WebWorld
GPU memory needed (smallest version of each): WebWorld 8B about 21.6 GB, WebWorld 14B about 36.8 GB, WebWorld 32B about 79 GB. The cheapest runs on Nvidia P40 from $0.13/h right now.
3 models (8B to 32B) · ↓ 0 downloads a month · from $0.13/h on Nvidia P40 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 |
|---|---|---|---|---|
| Onnx (onnx-community)onnx-community/WebWorld-8B-Onnx | ONNX Runtime GenAI | 16 GB | 21.6 GB | $0.13/h Nvidia P40 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Onnx (onnx-community)onnx-community/WebWorld-14B-Onnx | ONNX Runtime GenAI | 30 GB | 36.8 GB | $0.32/h Quadro RTX 8000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Onnx (onnx-community)onnx-community/WebWorld-32B-Onnx | ONNX Runtime GenAI | 66 GB | 79 GB | $1.22/h Nvidia A100 |
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").