Protein Structure · biohub
Accelerated variant of ESMFold2 — optimised for high-throughput structure prediction across large protein sets while retaining strong accuracy.
< 1s
Runs on On-demand GPU
Runs on our servers with on-demand compute. A first run needs time to load the model; active capacity can be reused and scales down when idle.Run this model
About this model
Accelerated variant of ESMFold2 — optimised for high-throughput structure prediction across large protein sets while retaining strong accuracy. Served on the Modal runner through EvolutionaryScale's own `esm` package, which pulls biohub/ESMFold2-Fast from the Hugging Face Hub. Inputs and outputs are what that adapter returns, not what the repository's pipeline tag says — check the model card before relying on a result.
Standardized I/O contract
Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.
Inputs
Protein sequence
Outputs
All-atom coordinates in PDB format, viewable and downloadable.
Residue count, mean pLDDT (0–100) and pTM.
