I’m intrigued by NVIDIA’s elastic and diffusion models. Do y’all have any experience with either of them? Is there any reason these two techs couldn’t work in the same model?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | 31 | 2558 | June 10, 2026 | |
| NVIDIA Nemotron TwoTower 30B-A3B - Anyone tried this out yet? | 1 | 312 | July 7, 2026 | |
| NVIDIA Nemotron Elastic | 0 | 238 | May 14, 2026 | |
| NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 - Not good at following simple instructions | 1 | 521 | April 5, 2026 | |
| nvidia/Nemotron-Cascade-2-30B-A3B yet another model to test | 19 | 1754 | March 24, 2026 | |
| DGX Spark, Nemotron3, and NVFP4: Getting to 65+ tps | 14 | 2400 | December 22, 2025 | |
| Guide for fine-tuning NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 to add new programming language support | 1 | 510 | April 29, 2026 | |
| nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 | 17 | 1560 | July 13, 2026 | |
| NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | 89 | 10948 | March 31, 2026 | |
| It's been a week since Nvidia released bunch of NVFP4 models. Any particular favourites? | 1 | 358 | February 16, 2026 |