tzakharko/m4-sme-exploration

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

Community benchmark database for running LLMs on Apple Silicon Macs

Community-driven benchmark suite for MLX inference engines on Apple Silicon

Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

Swift API for MLX

Qwen 3.6 - llama.cpp (with or without MTP) vs mlx-ml benchmark

Apple GPU microarchitecture

Low-level Metal inference engine for Apple M4: universal quant formats at MLX parity, 1M-token out-of-core contexts, and speculative decode off flash storage.