Home / 🧱 AI Foundation Stack / ⚡ Inference / Serving

AnkitNayak-eth/llmBench

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing deep hardware intelligence.

🧱 AI Foundation Stack ✓ Commercial OK ★ 45Python

Commercial license

✓ Commercial OKMIT

可商用,通常只需保留著作權聲明/授權條款

Topics

ai-benchmarkllmllm-inferencellm-toolslocal-llm
Ad