{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "lithos-ai-lithos-metal--compare-draft-and-target-only-generation",
 "repo": "lithos-ai/lithos-metal",
 "repo_url": "https://github.com/lithos-ai/lithos-metal",
 "repo_slug": "lithos-ai-lithos-metal",
 "title": "Compare speculative and target-only generation",
 "page_title": "How to compare speculative and target-only generation with Lithos Metal",
 "summary": "Run the same model with DSpark drafting on and off to see how the setting changes output speed.",
 "who": "A performance-minded developer who wants to check whether DSpark speculative decoding helps on their own Mac and workload.",
 "problem": "The README gives projections, not end-to-end results for every machine, so the developer needs to measure the difference locally.",
 "outcome": "Two server runs, one with the default DSpark draft and one with target-only generation, with timings recorded for the same prompt.",
 "steps": [
  "Install the package with `brew install lithos-ai/tap/lithos-metal`.",
  "Start the default server with `lithos-metal serve --model nvidia/Qwen3.8-27B-NVFP4` and time a fixed prompt with the curl call from the README.",
  "Stop the server and restart it with `lithos-metal serve --model nvidia/Qwen3.8-27B-NVFP4 --no-draft`. (inferred, check the README)",
  "Repeat the same timed prompt and record the tokens per second for both runs."
 ],
 "agent_prompt": "Using the lithos-metal repo at https://github.com/lithos-ai/lithos-metal, run the same fixed prompt against `lithos-metal serve --model nvidia/Qwen3.8-27B-NVFP4` and again with `--no-draft`. Report wall-clock time and generated token count for each run in a two-row table. Verify both runs used the same prompt and max_completion_tokens before comparing.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 hour 30 minutes",
 "basis": "readme",
 "caveat": "The README warns that its own speed figures exclude drafting and rewind and are not end-to-end comparisons, so your timings only apply to your machine, model, and prompt.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "An Apple silicon Mac running macOS 26 or later",
  "Enough unified memory for the target model, draft model, and context (the README tests Qwen models on a 40-core M5 Max with 48 GB)",
  "Homebrew, or Xcode Command Line Tools and Python 3.12 for a source build",
  "Client tools such as opencode, claude, codex, or hermes installed separately, if you use the launchers"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/lithos-ai-lithos-metal/compare-draft-and-target-only-generation/",
 "md": "https://dedupedai.com/use-cases/lithos-ai-lithos-metal/compare-draft-and-target-only-generation/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/lithos-ai-lithos-metal--compare-draft-and-target-only-generation.json",
 "api_version": "v1"
}