Blackwell
FP4 Just Landed in llama.cpp: NVFP4 vs MXFP4 Explained (2026)
NVFP4 in llama.cpp, MXFP4 in ik_llama.cpp. The first practical FP4 quantization for the GGUF ecosystem — what works, what doesn't, and what to test.
Best Docker Setup for Local AI: Ollama + Open WebUI (2026)
Five copy-paste Docker compose recipes for Ollama 0.24 + Open WebUI: NVIDIA Blackwell, AMD ROCm, multi-GPU, and CPU. Plus the Apple Silicon catch most guides skip.
RTX 5060 Ti Review for Local AI — The New Budget King
Real benchmarks for the RTX 5060 Ti 16GB running local LLMs. Qwen 3.5 35B at 44 tok/s, 100K context for ~$430. Compared against RTX 3060, 3090, and 4060 Ti.