{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "ArtificialAnalysis/aa-agentperf-local",
 "name": "aa-agentperf-local",
 "owner": "ArtificialAnalysis",
 "slug": "artificialanalysis-aa-agentperf-local",
 "github": "https://github.com/ArtificialAnalysis/aa-agentperf-local",
 "what": "agentperf-local is an open-source tool that replays recorded agent conversations against a local OpenAI-compatible model server to measure throughput and latency.",
 "why": "",
 "language": "Python",
 "requirements": [
  "uv installed (it fetches Python 3.12 if needed)",
  "A model server you already run with an OpenAI-compatible API, or a framework the tool can start (llama.cpp, vLLM, SGLang, or Splash on Apple Silicon)",
  "For full results, a server or device that can run a 65,536-token context at batch size 1",
  "Docker only if you want live tool calling"
 ],
 "audience_note": "Built for people who run local LLM servers and want to know how fast their machine serves an AI agent, plus AI agents that run these benchmarks for them.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/",
 "use_case_count": 5,
 "use_cases": [
  {
   "id": "artificialanalysis-aa-agentperf-local--benchmark-attached-local-server",
   "title": "Benchmark a local model server you already run",
   "best": true,
   "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/benchmark-attached-local-server/",
   "json": "https://dedupedai.com/use-cases/u/artificialanalysis-aa-agentperf-local/benchmark-attached-local-server.json"
  },
  {
   "id": "artificialanalysis-aa-agentperf-local--managed-run-pinned-catalog-model",
   "title": "Download and benchmark a pinned catalog model",
   "best": false,
   "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/managed-run-pinned-catalog-model/",
   "json": "https://dedupedai.com/use-cases/u/artificialanalysis-aa-agentperf-local/managed-run-pinned-catalog-model.json"
  },
  {
   "id": "artificialanalysis-aa-agentperf-local--quick-install-check-small-context",
   "title": "Check a setup quickly with the mini replay",
   "best": false,
   "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/quick-install-check-small-context/",
   "json": "https://dedupedai.com/use-cases/u/artificialanalysis-aa-agentperf-local/quick-install-check-small-context.json"
  },
  {
   "id": "artificialanalysis-aa-agentperf-local--benchmark-splash-on-apple-silicon",
   "title": "Benchmark Qwen on Splash on an Apple Silicon Mac",
   "best": false,
   "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/benchmark-splash-on-apple-silicon/",
   "json": "https://dedupedai.com/use-cases/u/artificialanalysis-aa-agentperf-local/benchmark-splash-on-apple-silicon.json"
  },
  {
   "id": "artificialanalysis-aa-agentperf-local--live-tool-calling-benchmark",
   "title": "Measure real tool time with live Docker tool calls",
   "best": false,
   "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/live-tool-calling-benchmark/",
   "json": "https://dedupedai.com/use-cases/u/artificialanalysis-aa-agentperf-local/live-tool-calling-benchmark.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}