Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.
Like TristanBilot/mlx-benchmark, 0 likes 0 Bookmark TristanBilot/mlx-benchmark, 0 bookmarks 0 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.
Like john-rocky/apple-silicon-llm-bench, 0 likes 0 Bookmark john-rocky/apple-silicon-llm-bench, 0 bookmarks 0 MLX: An array framework for Apple silicon
Like ml-explore/mlx, 0 likes 0 Bookmark ml-explore/mlx, 0 bookmarks 0 A tutorial on Apple MLX and LLM
Like ddttom/mlx-llm-tutorial, 0 likes 0 Bookmark ddttom/mlx-llm-tutorial, 0 bookmarks 0 PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.
Like Epistates/pmetal, 0 likes 0 Bookmark Epistates/pmetal, 0 bookmarks 0 MLX-compatible Vulkan and ANE backends for Apple Silicon running Linux.
Like joshuaswarren/omarchy-mlx, 0 likes 0 Bookmark joshuaswarren/omarchy-mlx, 0 bookmarks 0 Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.
Like trevin-creator/autoresearch-mlx, 0 likes 0 Bookmark trevin-creator/autoresearch-mlx, 0 bookmarks 0 
