Quick Start
openclaw skills install llamacpp-benchllama.cpp Benchmark
byalexhegit · crypto
Run llama.cpp benchmarks on GGUF models to measure prompt processing (pp) and token generation (tg) performance. Use when the user wants to benchmark LLM models, compare model performance, test inference speed, or run llama-bench on GGUF files. Supports Vulkan, CUDA, ROCm, and CPU backends.
openclaw skills install llamacpp-bench Or ask OpenClaw: "Install the llama.cpp Benchmark skill"
Try llama.cpp Benchmark with OpenClaw Cloud
Install and run llama.cpp Benchmark instantly — no setup required.