The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI API compatible, zero API keys.

🔥 Alternative to Ollama — multi-model serving with sub-ms model switching · CPU-only 20B inference for Edge AI · llama.cpp + stablediffusion.cpp

⚡️ The fastest way to run local LLMs on Apple Silicon — sub-second model loads, beats Ollama on throughput, tail latency, and full-response time. OpenAI/Ollama-compatible. No cloud, no API keys.

The Ollama developer experience with the vLLM production power. Deploy local LLMs via Docker with smart and automatic GPU VRAM management.

Run MoE models bigger than your RAM — expert weights page from SSD on demand, byte-identical output. Mixtral 26GB in 3.3GB RSS on a MacBook Air.

On-premise OpenAI-compatible AI gateway & management UI. Securely run, orchestrate, and hot-swap local LLMs (GGUF) within your private perimeter. Built with .NET 10 & llama.cpp.

caix — native Apple Core AI inference server for Apple silicon (beta): OpenAI/Anthropic API, dashboard, streaming chat with tools/skills/MCP, MTP speculative decoding.

Local AI platform: run LLMs, Stable Diffusion, Whisper, TTS, video & 3D generation offline — open-source Ollama + ComfyUI alternative in one binary.

Local LLM gateway for Apple Silicon. Works with OpenClaw, Hermes Agent, Claude Code, and Codex (AIRun). No Ollama or LM Studio required.

Web frontend for LM Studio — browser access, adaptive memory, multi-user auth, MCP tools

Local OpenAI-compatible proxy with real failover, multi-account aliasing, and ChatGPT Plus/Pro as a backend. Single ~11MB binary, no Docker, secrets in OS keyring. Windows/macOS/Linux.

A unified local AI workspace — chat with GGUF models (Qwen, Llama, Phi), generate images, and share your AI remotely. Features agentic web search.

Route LLM API requests through a local proxy with multi-account support, failover, and secure key storage.

OllamoMUI — #1 FREE Ollama alternative: local LLM proxy to 26 free models (OpenRouter/OpenAI/Anthropic/Groq/DeepSeek/Gemini) with RAG, memory & dashboard. Built by Rakibul Hasan (Rhasan@dev), a Dhaka, Bangladesh full-stack dev open to remote/WFH/freelance. Hire me for full-stack, backend & AI/LLM work.

One-click installer for Google Gemma 4 12B — optimized to run on 8GB laptops, 1M context, native multimodal. No terminal. Win/Mac, MIT.

Local LLM inference + embedding & search in one package. Run 30B on consumer hardware, RAG without ChromaDB.

In the style of Claude Chat Pro — fully local on Apple Silicon. oMLX (vision + speed) + Open Interpreter (unrestricted sandbox) + rich Artifacts + attachments (PDF, JSON, Markdown, PNG, JPEG) + paste support.

Run local LLMs the easy way. CLI + KDE Plasma 6 widget. Wraps llama.cpp in Docker. No telemetry.