Unknown family
on NVIDIA RTX 5070 · llama.cpp
Sep 23, 2026
Summary
User reports that after AUR llama.cpp-cuda package deletion, binary packages (ggml-cuda and llama.cpp) are ~10% speed, with model loaded to GPU but processing on CPU. Custom build achieves 1800 t/s prefill vs 150 t/s. GPU is RTX 5070.