{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "artificialanalysis-aa-agentperf-local--managed-run-pinned-catalog-model",
 "repo": "ArtificialAnalysis/aa-agentperf-local",
 "repo_url": "https://github.com/ArtificialAnalysis/aa-agentperf-local",
 "repo_slug": "artificialanalysis-aa-agentperf-local",
 "title": "Download and benchmark a pinned catalog model",
 "page_title": "How to download and benchmark a pinned catalog model with Aa Agentperf Local",
 "summary": "Let the tool fetch a verified model, start llama.cpp, run the replay, and stop the server.",
 "who": "A local AI enthusiast or hardware reviewer who wants a reproducible benchmark of a specific model on their own machine.",
 "problem": "Setting up a model server, pinning the exact model files, and running a comparable replay by hand is error-prone.",
 "outcome": "A results directory with the replay summary, plus the server log and deployment record written by the managed run.",
 "steps": [
  "Install the tool with `uv tool install agentperf-local`",
  "Make sure `llama-server` is on your PATH",
  "Run `agentperf-local managed-run --profile-id qwen38-27b-q4-k-m --framework llama-cpp --output-dir results/qwen38-27b` (inferred, check the README)",
  "Check summary.json and the server log in results/qwen38-27b"
 ],
 "agent_prompt": "Using the agentperf-local repo from ArtificialAnalysis, run `agentperf-local managed-run` with --profile-id qwen38-27b-q4-k-m and --framework llama-cpp, writing to results/<name>. Expect a summary.json and a server log in that directory. Verify that every model file passed its SHA-256 check and that the run is not marked reduced.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "A full comparable run needs a 65,536-token context at batch size 1, so a device that cannot fit it can only produce a reduced run that is not comparable with full results.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "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"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/managed-run-pinned-catalog-model/",
 "md": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/managed-run-pinned-catalog-model/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/artificialanalysis-aa-agentperf-local--managed-run-pinned-catalog-model.json",
 "api_version": "v1"
}