silicon-eval is an open-source CLI tool designed for evaluating and profiling large language models (LLMs) specifically on Apple Silicon devices. It provides benchmarking, profiling, and quantization analysis to help AI researchers and developers optimize model performance. The tool supports MLX and is distributed under the MIT license.
silicon-eval sits in PulseGate's LLM eval & observability category. It enables developers to benchmark and profile large language models on Apple Silicon hardware efficiently. silicon-eval is an open-source project aimed at AI researchers and developers working with LLMs on Apple Silicon. The project is open source (MIT). silicon-eval is available on the command line.
Behind silicon-eval is Indy102, and the product first shipped in 2026. The project is developed in the open on GitHub with 42 commits in the last 90 days. Among its 5 catalogued features are LLM benchmarking, profiling tools, and Apple Silicon support.
Latest indexed changes and source events
Other apps tracked under the same category.
