TristanBilot/mlx-benchmark

Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.

53
/ 100
Established

This tool helps machine learning engineers and researchers understand the performance of MLX operations on various Apple Silicon chips (M1-M4) and compare them against PyTorch on Apple's MPS, CPU, and NVIDIA CUDA GPUs. It takes your specified hardware and MLX/PyTorch versions as input, and outputs detailed or averaged runtime benchmarks for different machine learning operations. It's ideal for those optimizing machine learning models for Apple hardware.

217 stars.

Use this if you are developing machine learning applications and need to compare the speed and efficiency of different ML frameworks and hardware configurations for specific operations.

Not ideal if you are looking for a high-level application performance monitor or a tool to benchmark entire machine learning model training workflows rather than individual operations.

machine-learning-engineering deep-learning-optimization hardware-benchmarking model-deployment performance-tuning
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

217

Forks

30

Language

Python

License

MIT

Last pushed

Mar 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TristanBilot/mlx-benchmark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.