M

SiliconLM

Power at the Edge.

The native dashboard for running Local LLMs on Apple Silicon. Performance monitoring, model management, and inference in one place.

Machine Info

Chip model, GPU cores, Neural Engine, RAM, and disk usage at a glance. Optimized for M-series chips.

MLX Embeddings

OpenAI-compatible /v1/embeddings API with Metal acceleration. Drop-in replacement for any embedding workflow.

Multi-Backend

MLX, mlx-lm for decoder models, and sentence-transformers. Choose the best backend for each model.

Service Management

Start and stop LMStudio, MLX Embeddings, and OpenCode services directly from the dashboard.

Smart Proxy

Single endpoint routes /v1/embeddings to MLX and /v1/chat to LMStudio automatically.

Model Downloads

Search HuggingFace and download models with aria2 acceleration. Resume interrupted downloads.

Ready to run?

terminal — -zsh — 80x24
$ git clone https://github.com/nxxxsooo/siliconlm.git
$ cd siliconlm
$ ./install.sh

Requires macOS 14.0+ and Apple Silicon (M series)