Hello. I’m currently working with the diffusion-fwi model of physicsnemo. Could you please share how many GPUs were used during training, and roughly how long it took to arrive at your results? Thank you.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Default reasoning effort for `openai/gpt-oss-120b`? | 1 | 136 | April 11, 2026 | |
| nvFP4 training - Playbook request | 12 | 556 | March 16, 2026 | |
| Community Docker adds support for DiffusionGemma | 36 | 2168 | June 14, 2026 | |
| nvidia/Nemotron-Cascade-2-30B-A3B yet another model to test | 19 | 1702 | March 24, 2026 | |
| Train a Reasoning-Capable LLM in One Weekend with NVIDIA NeMo | 16 | 710 | August 17, 2025 | |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | 31 | 2448 | June 10, 2026 | |
| nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 | 17 | 1446 | July 13, 2026 | |
| NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 - Not good at following simple instructions | 1 | 501 | April 5, 2026 | |
| Request for NVIDIA NIM API Rate Limit Increase for Academic Study Project | 0 | 127 | May 8, 2026 | |
| Many models are very very slow to start answer or thinking | 0 | 550 | April 26, 2026 |