Loading…
Loading…
Models / Llama-3
1 model (8B) · ↓ 26K downloads a month · from $0.18/h on 2x 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 |
|---|---|---|---|---|
| Llama 3 8B Instruct v0.9MaziyarPanahi/Llama-3-8B-Instruct-v0.9 | vLLM | 16 GB | 21.3 GB | $0.18/h 2x RTX 3060 |
| Llama 3 8B Instruct v0.8MaziyarPanahi/Llama-3-8B-Instruct-v0.8 | vLLM | 16 GB | 21.3 GB | $0.18/h 2x RTX 3060 |
| Llama 3 8B Instruct v0.10MaziyarPanahi/Llama-3-8B-Instruct-v0.10 | vLLM | 16 GB | 21.3 GB | $0.18/h 2x 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").