ARM architecture central processing units are increasingly prevalent in high-performance computers due to their energy efficiency, scalability, and cost-effectiveness. The overall goal of this study is to evaluate the suitability of ARM-based cloud computing instances in executing finite element computations. Specifically, we present performance results for running the FEniCS Project finite element software on Amazon Web Services (AWS) c7g and c7gn instances with Graviton3 processors. These processors support the ARMv8.4-A instruction set with Scalable Vector Extension (SVE) for Single Instruction Multiple Data operations and the Elastic Fabric Adaptor for communications between instances. Both clang 18 and GNU Compiler Collection 13 compilers successfully generated optimised code using SVE instructions, ensuring that users can achieve optimised performance without extensive manual tuning. Testing a distributed memory parallel DOLFINx Poisson solver with up to 512 Message Passing Interface processes, we find that the performance and scalability of the AWS instances are comparable to those of a dedicated AMD EPYC Rome cluster installed at the University of Luxembourg. These findings demonstrate that ARM-based cloud computing instances, exemplified by AWS Graviton3, can be competitive for distributed memory parallel finite element analysis.