{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "peonist-ai-halogen-server--benchmark-prefill-decode-on-own-hardware",
 "repo": "peonist-ai/halogen-server",
 "repo_url": "https://github.com/peonist-ai/halogen-server",
 "repo_slug": "peonist-ai-halogen-server",
 "title": "Measure prefill and decode speed on your own machine",
 "page_title": "How to measure prefill and decode speed on your own machine with Halogen Server",
 "summary": "Run the bundled sweep and bench tools to get reproducible tokens-per-second figures.",
 "who": "A performance-minded engineer who needs real throughput numbers for their own Strix Halo box before choosing a local model setup.",
 "problem": "Published speed figures for local models vary by prompt and configuration, so quoted numbers are hard to compare.",
 "outcome": "A set of prefill and decode figures measured on the user's own hardware, with the prompt set and version named.",
 "steps": [
  "Download the checkpoint and tokenizer as described for the endpoint setup.",
  "Run the ten-shape benchmark with `podman run --rm --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined --ipc=host -v /path/to/models:/models:ro -v /path/to/tokenizer:/tokenizer:ro ghcr.io/peonist-ai/halogen:0.1.4 bench dflash2 256 low 3`. (inferred, check the README)",
  "Run the llama-bench-shaped sweep with `podman run --rm ... ghcr.io/peonist-ai/halogen:0.1.4 sweep -p 512,2048,8192 -n 128,256 -d dflash2,mtp -r 3` (add the same device and volume flags as the bench command). (inferred, check the README)",
  "Add `--json` to the sweep command if you want machine-readable output.",
  "Record the version, the drafter, and the prompt set next to every number you publish."
 ],
 "agent_prompt": "Using the repo peonist-ai/halogen-server, run the bench and sweep commands from its README against the models at <models_path> on this machine. Expected output: prefill tokens per second for each prompt length and decode mean and range for each drafter. Verify that each reported figure names the version 0.1.4 and the prompt set.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "Decode speed on this engine varies with the prompt type, so a single number is not meaningful unless the prompt set is named.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "AMD Strix Halo machine (Radeon 8060S class GPU, gfx1151) with /dev/kfd and /dev/dri available",
  "Podman (or Docker with the video and render group flags described in the README)",
  "About 36 GB of free disk for the 35.9 GB checkpoint, plus the 3.5 GB image",
  "Python with pip to install the Hugging Face CLI"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/peonist-ai-halogen-server/benchmark-prefill-decode-on-own-hardware/",
 "md": "https://dedupedai.com/use-cases/peonist-ai-halogen-server/benchmark-prefill-decode-on-own-hardware/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/peonist-ai-halogen-server--benchmark-prefill-decode-on-own-hardware.json",
 "api_version": "v1"
}