---
title: "Nvidia's new runtime nearly triples protein-folding throughput"
url: https://www.parallelquant.com/posts/nvidia-s-new-runtime-nearly-triples-protein-folding-throughput-534a8a
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/09/10/nvidia-details-bionemo-inference-runtime-bioir-2-90x-higher-boltz-2-folding-throughput-and-58-5k-residues-per-gpu-hour-on-8xh100/
published: 2026-09-10T21:57:06.000Z
topics: ["research", "chips"]
publisher: "Parallel Quant"
---

# Nvidia's new runtime nearly triples protein-folding throughput

*2026-09-10 · Source: [MarkTechPost](https://www.marktechpost.com/2026/09/10/nvidia-details-bionemo-inference-runtime-bioir-2-90x-higher-boltz-2-folding-throughput-and-58-5k-residues-per-gpu-hour-on-8xh100/)*

Nvidia detailed BioNeMo Inference Runtime (BioIR), a library that speeds up biomolecular structure-prediction models while staying in standard PyTorch. In an 8-GPU benchmark it delivered 58,500 folded residues per GPU-hour with the Boltz-2 model, a 2.9x gain over a torch-compiled baseline, and it already powered an AlphaFold Database expansion generating about 31 million candidate protein complexes.

**Why it matters:** Faster, cheaper protein-structure inference lowers the cost of large-scale computational biology, a key input for drug discovery. It's another example of AI infrastructure gains translating directly into scientific throughput rather than just chatbot performance.

**Topics:** research, chips

---
Read the original: https://www.marktechpost.com/2026/09/10/nvidia-details-bionemo-inference-runtime-bioir-2-90x-higher-boltz-2-folding-throughput-and-58-5k-residues-per-gpu-hour-on-8xh100/
Canonical: https://www.parallelquant.com/posts/nvidia-s-new-runtime-nearly-triples-protein-folding-throughput-534a8a
Published by Parallel Quant — https://www.parallelquant.com