Loading…
Loading…
Models / Wizard-Vicuna
GPU memory needed (smallest version of each): Wizard-Vicuna 13B about 18 GB. The cheapest runs on RTX 3090 from $0.20/h right now.
1 model (13B) · ↓ 53 downloads a month · from $0.20/h on RTX 3090 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 |
|---|---|---|---|---|
| OriginalTheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ | vLLM | 7.5 GB | 18 GB | $0.20/h RTX 3090 |
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").