Check out how nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 achieved 116.84 tokens/sec on text generation on NVIDIA DGX Spark with vLLM!
View full benchmark at nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 - Spark Arena Benchmark
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| [Benchmark] nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 | 5 | 1523 | May 1, 2026 | |
| New Nemotron 3.5 Lighting 30B-A3B | 6 | 1359 | August 12, 2026 | |
| Nemotron-3-Super-120B-A12B-NVFP4 on single DGX Spark: 23.45 tok/s (spark-arena.com/ benhmarks) | 6 | 1294 | May 26, 2026 | |
| NVIDIA Nemotron-3.5-Lightning-30B-A3B-NVFP4: DGX Spark vs. RTX PRO 6000 Blackwell Performance | 0 | 304 | August 12, 2026 | |
| NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | 89 | 11164 | March 31, 2026 | |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | 31 | 2651 | June 10, 2026 | |
| Nemotron-3-Super-120B at 20-22 tok/s Super Special Recipe | 4 | 1001 | May 30, 2026 | |
| DGX Spark, Nemotron3, and NVFP4: Getting to 65+ tps | 14 | 2452 | December 22, 2025 | |
| nvidia/Nemotron-Cascade-2-30B-A3B yet another model to test | 19 | 1814 | March 24, 2026 | |
| Nemotron 3 Super: Updates Approaching Agentic Usability | 1 | 524 | April 5, 2026 |