Ultra-fast, zero-dependency CPU-only LLM runner & OpenAI micro-server. Run GGUF models on system RAM with speculative decoding (No VRAM / No CUDA).
golang simd avx2 cursor quantization cline avx-512 no-gpu openai-api cpu-inference llm llama-cpp local-ai gguf speculative-decoding deepseek-r1 roo-code zero-vram
-
Updated
Nov 2, 2026 - Go