local-llm

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache — fused NEON kernels, Metal/MPS compute, exact reproducible decoding, and an OpenAI-compatible API server for local chat and coding agents.

Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.

Reame — CPU-first LLM inference server on llama.cpp: disk KV cache, self-regulating speculation, generation archive, interleaved multi-user, the Conclave. Your hardware, your realm.

An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.

HotPin: routing-guided expert pinning for lossless low-RAM MoE inference on consumer CPU+NVMe - 120B model at 3.84 tok/s in 19 GB RAM, no GPU