Writing · Tag

#gpu-offloading

1 post tagged #gpu-offloading.

Apr 6, 20267 min read
llama.cpp n_gpu_layers Explained: -1, 0 & VRAM Guide
n_gpu_layers -1 offloads every layer to GPU. Learn what each value means, the exact VRAM math, and pick the right setting with real benchmarks.
#llama-cpp#local-llm#gpu-offloading#n-gpu-layers

The weekly AI automation breakdown

Real costs, real tools, no fluff. One email per week with what I'm building, what's working, and what's not.