Loading…
Loading…
Models / Llama-3_3-Nemotron-Super
4 models (49B to 49B) · ↓ 238.5K downloads a month · from $0.89/h on 2x Nvidia A40 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_3-Nemotron-Super-49B-v1_5 | vLLM | 100 GB | 136.9 GB | $1.38/h 8x RTX 3090 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8 | vLLM | 52 GB | 83.8 GB | $0.89/h 2x Nvidia A40 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/Llama-3_3-Nemotron-Super-49B-v1 | vLLM | 100 GB | 136.9 GB | $1.38/h 8x RTX 3090 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4 | vLLM | 31 GB | 60.6 GB | $0.89/h 2x Nvidia A40 |
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").