Loading…
Loading…
Models / solar-pro-preview
1 model (~22.1B) · ↓ 5.6K downloads a month · from $0.72/h on 4x RTX 5060 Ti 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 |
|---|---|---|---|---|
| Originalupstage/solar-pro-preview-instruct | vLLM | 44 GB | 52.9 GB | $0.72/h 4x RTX 5060 Ti |
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").