Loading…
Loading…
Models / Llama-3
3 models (8B to 70B) · ↓ 35K downloads a month · from $0.19/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 |
|---|---|---|---|---|
| Originalgradientai/Llama-3-8B-Instruct-Gradient-1048k | vLLM | 16 GB | 21.3 GB | $0.19/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalgradientai/Llama-3-8B-Instruct-262k | vLLM | 16 GB | 21.3 GB | $0.19/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalgradientai/Llama-3-70B-Instruct-Gradient-1048k | vLLM | 141 GB | 162 GB | $2.23/h 8x 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").