HyPLM-Flash (Tencent Hyra)
HyPLM-Flash (Tencent Hyra) is a protein structure & design tool whose code is published by Tencent-Hunyuan on GitHub, first public in 2026. 650M-parameter protein language model trained by Tencent's Hyra 2.0 agent, with an INT8 engine embedding ~130k residues/s on one H20; ProteinGym zero-shot Spearman 0.409, tied with ESM-2 650M and ESM C 600M.
| Category | Protein structure & design |
|---|---|
| Developer (GitHub) | Tencent-Hunyuan |
| Input | Protein sequence |
| Task | Protein embeddings, masked-LM zero-shot mutation scoring |
| Interface | Python package and CLI; CUDA GPU required |
| Website | github.com/Tencent-Hunyuan/Hyra-results/tree/main/AI4Science/hyplm_flash |
| GitHub | Tencent-Hunyuan/Hyra-results |
| First public | 2026-11-02 (source) |
| Code license | MIT |
| Weights license | FP32 weights (2.6 GB) distributed as a GitHub Release, no separate weights license stated |
| What this allows | Permissive (commercial OK) Use, modify and ship it inside closed-source commercial products; keep the license text and copyright notices. What do these mean? |
| License source | github.com/Tencent-Hunyuan/Hyra-results/blob/main/AI4Science/hyplm_flash/README.md · checked 2026-11-02 |
| Pricing | Open source |
| Tags | #protein-language-model#embeddings#variant-effect |
| Last checked | · links verified |
Can I use HyPLM-Flash (Tencent Hyra) commercially?
Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices.
- Code: MIT
- Weights: FP32 weights (2.6 GB) distributed as a GitHub Release, no separate weights license stated
- Source: github.com/Tencent-Hunyuan/Hyra-results/blob/main/AI4Science/hyplm_flash/README.md · license checked 2026-11-02
What the license types mean · not legal advice.
Specs
| Task | Protein embeddings, masked-LM zero-shot mutation scoring |
|---|---|
| Modalities | Protein sequence |
| MSA required | No (single sequence) |
| Open weights | Yes (GitHub Release) |
| GPU need | CUDA GPU required (Hopper such as H20/H100 recommended) |
| GitHub stars | 177 |
| Interface | Python package and CLI; CUDA GPU required |
Compare with…
Pick 1–3 other Protein structure & design tools to compare side by side with HyPLM-Flash (Tencent Hyra).
Related
DeepMind's open-source protein structure prediction model (monomer and multimer).
Structure prediction of proteins, nucleic acids, ligands and their complexes; hosted web server plus open code, weights on request for non-commercial use.
Open biomolecular interaction models (Boltz-1, Boltz-2) for complex structure and binding-affinity prediction.