Ollama Benchmark - Compare LLMs Locally
Extension Actions
Benchmark and compare LLMs running on Ollama. Analyze token performance, export results, and optimize your AI workflows.
🔍 Benchmark and compare performance across LLMs (Large Language Models) like Mistral, LLaMA, Qwen, and others – powered by Ollama. This Chrome Extension allows you to test multiple models simultaneously and export detailed performance results.
🧠 Features:
- 📌 Select one or multiple models to compare
- 🧪 Run prompt-based benchmark tests
- 📊 Analyze token count, response time, and speed (Token/s)
- 💾 Export results in `.txt`, `.csv`, or `.json` format
- 🗂 Local storage of settings and results
- 🌐 Works with both local and remote Ollama APIs
- 🌍 Multilingual interface (English & Turkish)
☕ Like the tool? Support the developer:
https://www.buymeacoffee.com/elroy
🔐 No data is collected. All processing happens in your browser.
📦 100% free to use.