Loading…
Loading…
Models / fable-traces
GPU memory needed (smallest version of each): fable-traces ~4.02B about 12.1 GB. The cheapest runs on Nvidia P100 from $0.10/h right now.
1 model (~4.02B) · ↓ 104 downloads a month · from $0.10/h on Nvidia P100 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 |
|---|---|---|---|---|
| OriginalAliesTaha/fable-traces | vLLM | 8.0 GB | 12.5 GB | $0.17/h RTX A4000 |
| Main (onnx-community)onnx-community/fable-traces | ONNX Runtime GenAI | 8.1 GB | 12.1 GB | $0.10/h Nvidia P100 |
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").