Loading…
Loading…
Models / Llama-3.1-Minitron
1 model (4B) · ↓ 9.3K downloads a month · from $0.13/h on RTX A4000 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 |
|---|---|---|---|---|
| Originalnvidia/Llama-3.1-Minitron-4B-Width-Base | vLLM | 9.0 GB | 13.4 GB | $0.13/h RTX A4000 |
| Llama 3.1 Nemotron Nano 4B v1.1nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 | vLLM | 9.0 GB | 13.4 GB | $0.13/h RTX A4000 |
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").