Moore Threads MTT S5000 Runs ByteDance Protenix-v2 Biomolecular Model
摩尔线程官宣：MTT S5000 适配字节跳动 Protenix-v2 开源生物分子结构预测模型
The pairing shows domestic Chinese GPUs covering a scientific-computing workload that has largely run on Nvidia hardware, giving pharma companies and research institutes a non-Nvidia option for AI4S workloads. Readers evaluating compute suppliers for drug discovery or bioinformatics can weigh MTT S5000 against CUDA-based alternatives. The underlying model matters too, since Protenix-v2 is one of the few open-source bases rivalling AlphaFold 3 for protein and ligand complex prediction.
Moore Threads announced on 24 Sep 2026 that its MTT S5000 training-and-inference GPU card now fully supports end-to-end inference for Protenix-v2, the open-source biomolecular structure prediction model from ByteDance's Seed team.
Protenix-v2 was released in April 2026 and matches or exceeds DeepMind AlphaFold 3 on several core benchmarks.
The model offers high-accuracy end-to-end prediction of complexes involving proteins, DNA, RNA and small-molecule ligands.
With this adaptation, Moore Threads says it has completed engineering validation across three AI for Science scenarios: macromolecular structure prediction, whole-genome sequence modelling and clinical medical imaging.
摩尔线程官宣：MTT S5000 适配字节跳动 Protenix-v2 开源生物分子结构预测模型
IT之家 9 月 24 日消息，摩尔线程今天宣布，旗下训推一体智算卡 MTT S5000 正式完成了开源生物分子结构预测模型 Protenix-v2 的全链路推理支持。 据IT之家了解，Protenix-v2 开源模型由字节跳动 Seed 团队研发，发布于 2026 年 4 月，在多项核心基准测试中性能持平甚至超越 DeepMind AlphaFold 3，是目前全球少数能够对蛋白质、DNA、RNA 及小分子配体复合物进行高精度端到端预测的开源基座。 MTT S5000 此次适配，标志着摩尔线程实现了大分子结构预测、全基因组序列建模与临床医学影像三大 AI for Science（AI4S）核心场景的端到端工程验证，为国内药企及科研机构提供 AI4S 算力底座。
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Moore Threads, Protenix-v2, MTT S5000, ByteDance.
Source attribution: curated from IT之家. Cross-source corroboration: 2 independent sources have covered this development (including pandaily), confirming industry-wide signal strength.
- pandaily09-24 07:38Source