# NVIDIA — Protein Design with RFD4-Proteina and Hugging Face Spaces

- Company: NVIDIA (nvidia.com)
- Announced: 2026-10-21T12:39:49+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://huggingface.co/blog/nvidia/rfd4-proteina-protein-design
- Record: https://forck.live/items/25909-protein-design-with-rfd4-proteina-and-hugging-face-spaces
- Models affected: RFD4-Proteina, Proteina-Complexa

NVIDIA and the University of Washington's Institute for Protein Design are showing how to run RFD4-Proteina, their BioNeMo open model for programmable protein design, from a browser. The guide walks through setting a design context, generating binders, and building a repeatable workflow in two Hugging Face Spaces, one on dedicated GPUs and one on shared ZeroGPU capacity. RFD4-Proteina pairs a flow-matching model with an autoencoder that represents each amino acid, sugar, or nucleotide as an anchor-atom coordinate plus a learned latent vector, so the model generates sequences and all-atom structures together instead of handing off between separate backbone, sequence, and structure models. It can design proteins in contexts that include other proteins, small molecules, nucleic acids, glycans, metal ions, and modified amino acids. A thinking setting (low, medium, high) controls how much the model refines each design, trading more compute for designs more likely to pass in silico filters. NVIDIA says a benchmark across 24 protein-binding targets found high thinking produced 76.40 structurally distinct designs per GPU-hour that met the stated computational criteria, against 13.24 for Proteina-Complexa. Designs, annotated targets, and complexes download as CIF files that carry the design context for later sessions. NVIDIA is sponsoring free access to the dedicated Space from October 21 to November 4, 2026, after which the ZeroGPU Space remains free subject to Hugging Face account quotas.

## Evidence

Verbatim from https://huggingface.co/blog/nvidia/rfd4-proteina-protein-design:

> In a design benchmark across 24 protein-binding targets, RFD4-Proteina at high thinking produced 76.40 structurally distinct designs per GPU-hour that met the defined computational criteria*, compared with 13.24 for Proteina-Complexa, the second-strongest method in the benchmark.

---

Record: https://forck.live/items/25909-protein-design-with-rfd4-proteina-and-hugging-face-spaces
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md