ArcInfer Zero ARC GPU Engine
Fast local LLMs on an Intel laptop iGPU. A from-scratch inference engine for Intel integrated GPUs (Xe-LPG / Meteor Lake “Arc Graphics”; Xe2 / Xe3
InferBridge TPU Engine
InferBridge turns Intel Windows PCs into local AI workstations. It provides a Windows-first, OpenAI-compatible server with streaming chat, local vision chat, text embeddings, model lifecycle and recovery workflows, secure Hugging Face access, context-budget visibility, CPU/GPU/NPU device targeting, System Doctor diagnostics, hardware benchmarking, a built-in browser UI, and a deterministic mock engine.
OpenVino