{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "gufo-org-gufo--benchmark-gufo-against-llama-cpp",
 "repo": "gufo-org/gufo",
 "repo_url": "https://github.com/gufo-org/gufo",
 "repo_slug": "gufo-org-gufo",
 "title": "Compare Gufo speed with a llama.cpp baseline",
 "page_title": "How to compare Gufo speed with a llama.cpp baseline with Gufo",
 "summary": "Run Gufo's benchmark guide against optional llama.cpp reference builds on your own Strix Halo box.",
 "who": "A performance-minded developer who wants to check published Gufo throughput numbers on their own hardware.",
 "problem": "Published tokens-per-second figures are hard to trust without running the same workload on the same machine.",
 "outcome": "Your own measured prompt and generation rates next to a llama.cpp reference for the same model class.",
 "steps": [
  "Read docs/BENCHMARKS.md in the Gufo repo for the complete benchmark settings.",
  "Run `nix develop` to get profiling and evaluation tools.",
  "Run `nix shell .#llama-cpp-reference` to load the optional llama.cpp baseline. (inferred, check the README)",
  "Run the benchmark workload described in each model guide, such as the Qwen3.8 27B BENCHMARKS.md file.",
  "Record pp and tg numbers and compare them with the README table."
 ],
 "agent_prompt": "In the gufo repo, follow docs/BENCHMARKS.md to run the Qwen3.8 27B benchmark on <model path> against the llama.cpp reference. Report prompt processing and token generation rates in tok/s and compare them with the README figures. Verify the same model file and settings were used for both runs.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "3 hours",
 "basis": "readme",
 "caveat": "The README says peak numbers use specific short-prompt and repetitive-output workloads, so your results will differ unless you match the documented settings exactly.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "c++",
 "requirements": [
  "Linux x86-64 machine with AMD Strix Halo (gfx1151) and enough unified memory for the chosen model",
  "Podman with rootless GPU device access to /dev/kfd and /dev/dri",
  "Hugging Face CLI (hf) to download model weights",
  "Several tens of GB of free disk space for model files"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/gufo-org-gufo/benchmark-gufo-against-llama-cpp/",
 "md": "https://dedupedai.com/use-cases/gufo-org-gufo/benchmark-gufo-against-llama-cpp/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/gufo-org-gufo--benchmark-gufo-against-llama-cpp.json",
 "api_version": "v1"
}