NVIDIA and University of Washington Release RFD4-Proteina on Hugging Face Spaces
Current overview (not historical)
NVIDIA and the University of Washington have released the RFD4-Proteina protein design model on Hugging Face Spaces, offering browser-based visualization and tiered design capabilities (low, medium, high). Initially provided free of charge, NVIDIA announced that dedicated spaces will cease to be free after November 4, 2026, while ZeroGPU spaces will remain free. The model supports sequence and structure generation with adjustable design thinking levels.
Written with AI from the reporting · updated 10/21/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationOct 21, 00:00recorded Oct 21, 20:43single sourcerevised
RFD4-Proteina开源与Hugging Face空间免费试用
Read original source ↗ Hugging Face BlogReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject：
- nvidia
- Action：
- 发布BioNeMo开源模型并开放免费访问
- Object：
- RFD4-Proteina蛋白质设计模型
- Occurred (fact side)：
- Oct 21, 00:00
- Published (valid side)：
- Oct 21, 20:39
- First seen (known side)：
- Oct 21, 20:43
Fact stationSingle source · one-sided claimRevisedCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- Hugging Face BlogFirst-party sourceRelated fact: single sourceSource report revisedNVIDIA and University of Washington co-develop RFD4-Proteina for unified protein sequence and structure generation
Report first recorded Oct 21, 20:43
RFD4-Proteina is a BioNeMo open model that combines protein sequence and all-atom structure generation into a single flow-matching model, reducing workflow handoffs. It can generate proteins in complex molecular contexts including other proteins, small molecules, nucleic acids, glycans, metal ions, and modified amino acids. The model pairs an autoencoder with a flow model to generate sequences and structures together around supplied constraints such as target binders or catalytic motifs. Users can access the model for free on Hugging Face Spaces during a sponsorship period from October 21 to November 4, 2026.
Read original source ↗
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.