ai-performance

Open repos and models their makers tagged ai-performance, most starred first. The same for everyone.

AI on my own machineRepo

Local-LLM-Token-Speed-Studio-with-Ollama

Local LLM performance benchmarking studio built with Ollama to measure and analyze inference speed, token generation throughput, response latency, and model performance. Compare multiple locally hosted Large Language Models, monitor generation metrics, evaluate CPU-based inference and visualize benchmarking results through an interactive interface.

  • 2
  • Python
  • MIT
  • 1 d ago
Search GitHub and Hugging Face for ai-performance

Get , open it once and sign in. Then come back here and press the button again.