AReaL System Requirements (CPU, RAM, Disk)
System requirements for AReaL: CPU, RAM, and disk space.
AReaL is a large-scale asynchronous reinforcement learning (RL) system built to bridge foundation model training with modern agent-based applications. Developed by researchers from Tsinghua IIIS and Ant Group, it is optimized for efficiency and scalability, making it ideal for training reasoning and agentic models. Its fully asynchronous RL training paradigm delivers industry-leading throughput, and its flexible design lets you plug in black-box agent applications by simply replacing the base_url.
Requirements · AReaL
Min vCPU
2
Min RAM
4,096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8,192 MB
Rec Disk
20 GB
See the full tool page: AReaL →