Community benchmark database for running LLMs on Apple Silicon Macs

Hands-on CPU vs GPU benchmarks for Apple Silicon (M-series): PyTorch MPS, TensorFlow-Metal, MLX, and llama.cpp to measure TFLOP/s & tokens/sec and learn why GPUs accelerate training.

Pi extension that measures and displays model TPS in the status bar

Local LLM inference benchmarker. Measures TPS, TTFT, and VRAM pressure across context sizes — from 2K to 256K tokens. Works with llama.cpp, Ollama, LM Studio, and any OpenAI-compatible server.

Lightweight shell script to benchmark token generation speed (tok/s) across Ollama models running in Docker. Auto-discovers all installed models or accepts a custom list via CLI. Uses Ollama's internal eval_duration timing for accurate results — no dependencies beyond curl and awk.

Speedtest for AI. Test latency to every major AI provider from your terminal.

Simple tool for measuring inference engine performance under multi-user load

Test AI provider latency (TTFB, TTFT, TPS) in your CI/CD pipeline. Benchmark OpenAI, Anthropic, Google, and more.