Loading…
Loading…
Models / NVIDIA-Nemotron-3.5-Lightning
3 models (30B to 30B) · ↓ 1.8M downloads a month · from $0.10/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 |
|---|---|---|---|---|
| Originalnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 | vLLM | 22 GB | 26.7 GB | $0.34/h 2x RTX 5060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | vLLM | 66 GB | 75.8 GB | $0.89/h 2x Nvidia A40 |
| NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DSparknvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark | vLLM | 1.4 GB | 3.8 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 | vLLM | 66 GB | 75.8 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").