- Conduid
- Marketplace
- #cpu-inference
MCP servers tagged cpu-inference
5 live MCP servers tagged "cpu-inference", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with cpu-inference.
Rai
CPU-only LLM inference engine in pure Rust — 4-bit quantized models, hand-written AVX2 kernels, speculative decoding, and a local HTTP/MCP server. No GPU, no Python runtime.
Rai
CPU-only LLM inference engine in pure Rust — 4-bit quantized models, hand-written AVX2 kernels, speculative decoding, and a local HTTP/MCP server. No GPU, no Python runtime.
Local Jev
⚡ 100% offline, zero-cost drop-in alternative to TypeSafe Jev System One decision models in Rust (<18ms on CPU)
Realtime Voice Agent
CPU-only real-time voice agent with Silero VAD, faster-whisper ASR, MCP-wrapped FAISS RAG, Ollama, and Piper TTS.
Irodori Anime Voice Studio
Japanese anime voice design and reference voice cloning with local CPU inference, A/B playback, and Gradio MCP