DemandAnnouncement
UC Berkeley Hartwig Group fits a 120B-class model on a single DGX Spark using NVFP4 quantization
The lab uses LoRA fine-tuning on Nemotron 3 Super 120B-A12B for chemistry machine learning, bypassing multi-day cluster queues and running eight- to 24-hour training fits back-to-back.
- Place
- Berkeley
- Companies
- NVIDIA, UC Berkeley
- Source
- Nvidia news post, published Nov 16, 2026
- Published here
This fact was extracted from the source above and checked automatically: every number and company named here appears in it. When the same fact turns up in another filing or post, that source is added here instead of a second copy. Read the original before relying on it.