Nvidia
@nvidia·2.2M subscribers·2.7K videos
Accelerating Protein Structure Inference
Posted
September 10, 2025
Views
6,646
Likes
239
Engagement
3.60%
September 10, 2025
6,646
239
3.60%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
0:55Now PlayingAvailable now on CoreWeave and in Google Cloud’s G4 preview, you can launch an instance and fold your first protein in under 30 seconds.
Launch on Google Cloud G4
Launch on CoreWeave
Test drive NVIDIA NIM for biology
The NVIDIA RTX PRO 6000 Blackwell Server Edition sets a new benchmark for protein structure AI, optimized for ISVs in drug discovery, agtech, and beyond. OpenFold2 inference runs up to 4.8× faster than L40S, with MSA-GPU steps ~2× faster, shrinking cloud bills per structure. Its 96 GB GDDR7 and 1.6 TB/s bandwidth remove GPU-memory bottlenecks, letting you fold larger complexes, batch alignments, and densify tenants per card without sacrificing QoS. RTX PRO Blackwell’s hardware TEE and remote attestation satisfy pharma security reviews without custom engineering.
More information on NVIDIA RTX PRO 6000 Blackwell Server Edition and availability from global system partners
Subscribe to the NVIDIA AI Healthcare Newsletter
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
