Nemotron-3.5-Lightning-30B speed on every GPU
1 measured runs across 1 GPUs, fastest first.
| GPU | Quant | Engine | tok/s | Roofline | Share |
|---|---|---|---|---|---|
| RTX 5090 | NVFP4 | vLLM | 378.9 | 686.3 | 55% |
1 measured runs across 1 GPUs, fastest first.
| GPU | Quant | Engine | tok/s | Roofline | Share |
|---|---|---|---|---|---|
| RTX 5090 | NVFP4 | vLLM | 378.9 | 686.3 | 55% |