uncSoft/anubis-oss

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

Community benchmark database for running LLMs on Apple Silicon Macs

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing deep hardware intelligence.

macMLX brings local LLM inference to Apple Silicon with a first-class native macOS experience. No cloud, no telemetry, no Electron — just your Mac running models at full speed.

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

Benchmark your local LLMs: speed, memory, and quality, in one command. TUI leaderboard for Ollama, LM Studio, llama.cpp, and vLLM.

A cosy home for your LLMs.

personal LLM alchemy

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar