Loading…
Loading…
Models / Wizard-Vicuna
GPU memory needed (smallest version of each): Wizard-Vicuna 7B about 8.4 GB, Wizard-Vicuna 13B about 13.1 GB, Wizard-Vicuna 30B about 24.7 GB. The cheapest runs on RTX 3060 from $0.10/h right now.
3 models (7B to 30B) · ↓ 1.2K downloads a month · from $0.10/h on RTX 3060 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 |
|---|---|---|---|---|
| GPTQ (TheBloke)TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ | vLLM | 4.5 GB | 8.4 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| GPTQ (TheBloke)TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ | vLLM | 8.1 GB | 13.1 GB | $0.16/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| GPTQ (TheBloke)TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ | vLLM | 17 GB | 24.7 GB | $0.44/h RTX 5000 Ada |
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").