Loading…
Loading…
Models / Flora-Rewarder
GPU memory needed (smallest version of each): Flora-Rewarder ~27.8B about 68.7 GB. The cheapest runs on 4x RTX 3080 from $0.86/h right now.
1 model (~27.8B) · ↓ 461 downloads a month · from $0.86/h on 4x RTX 3080 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 |
|---|---|---|---|---|
| Originalnvidia/Flora-Rewarder | vLLM | 56 GB | 68.7 GB | $0.86/h 4x RTX 3080 |
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").