Loading…
Loading…
Models / vicuna
GPU memory needed (smallest version of each): vicuna 13B about 12.4 GB. The cheapest runs on RTX 4060 Ti from $0.17/h right now.
1 model (13B) · ↓ 266 downloads a month · from $0.17/h on RTX 4060 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 |
|---|---|---|---|---|
| Originalanon8231489123/vicuna-13b-GPTQ-4bit-128g | vLLM | 7.5 GB | 12.4 GB | $0.17/h RTX 4060 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").