Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

⚡️ 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.

Ultra-fast LLM inference engine — Vulkan backend, no CUDA required, AMD/Intel/NVIDIA