Community benchmark database for running LLMs on Apple Silicon Macs
-
Updated
Apr 22, 2026 - Shell
#
tokens-per-second
Here are 6 public repositories matching this topic...
🚀 Explore GPU capabilities on Mac with hands-on comparisons of CPU and Metal GPU performance for AI training using PyTorch and TensorFlow.
education benchmark deep-learning metal tensorflow gpu pytorch matrix-multiplication mps mlx hands-on apple-silicon llamacpp tflops tokens-per-second
-
Updated
Apr 28, 2026 - Python
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.
education benchmark deep-learning metal tensorflow gpu pytorch matrix-multiplication mps mlx hands-on apple-silicon llamacpp tflops tokens-per-second
-
Updated
Aug 17, 2025 - Python
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.
shell docker benchmarking benchmark gpu inference unraid compare token tokenization llm ollama llm-benchmark tokens-per-second ollama-benchmark
-
Updated
Apr 18, 2026 - Shell
Speedtest for AI. Test latency to every major AI provider from your terminal.
nodejs cli npm terminal command-line openai developer-tools mistral speed-test npx ttfb google-ai anthropic ai-performance ai-benchmark llm-benchmark tokens-per-second api-latency ai-latency ai-speed-test
-
Updated
Mar 9, 2026 - JavaScript
Test AI provider latency (TTFB, TTFT, TPS) in your CI/CD pipeline. Benchmark OpenAI, Anthropic, Google, and more.
testing devops automation ci-cd cloudflare openai developer-tools mistral ttfb google-ai github-actions ai-monitoring anthropic ai-performance ai-benchmark llm-benchmark tokens-per-second api-latency ai-latency ai-speed-test
-
Updated
Mar 9, 2026 - JavaScript
Improve this page
Add a description, image, and links to the tokens-per-second topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the tokens-per-second topic, visit your repo's landing page and select "manage topics."