https://ryanlupague.dev/tags/cuda/ Recent content in CUDA on Ryan Marcus Jeremy Lupague Hugo -- 0.125.6 en-us Sun, 15 Feb 2026 00:00:00 +0000 https://ryanlupague.dev/blogs/running-local-llm-models-with-llama-cpp/ Sun, 15 Feb 2026 00:00:00 +0000 https://ryanlupague.dev/blogs/running-local-llm-models-with-llama-cpp/ Notes on building llama.cpp with CUDA and tuning local GGUF model inference on an 8 GB RTX 4060 laptop GPU.