Loading…
Loading…
Models / Llama-3.2
GPU memory needed (smallest version of each): Llama-3.2 3B about 11.3 GB. The cheapest runs on RTX 3060 from $0.11/h right now.
1 model (3B) · ↓ 423 downloads a month · from $0.11/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 |
|---|---|---|---|---|
| Originalchuanli11/Llama-3.2-3B-Instruct-uncensored | vLLM | 7.2 GB | 11.3 GB | $0.11/h RTX 3060 |
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").