{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "fareedkhan-dev-kimi-k3-in-c--verify-identical-output-across-memory-presets",
 "repo": "FareedKhan-dev/kimi-k3-in-c",
 "repo_url": "https://github.com/FareedKhan-dev/kimi-k3-in-c",
 "repo_slug": "fareedkhan-dev-kimi-k3-in-c",
 "title": "Check that output stays identical across memory presets",
 "page_title": "How to check that output stays identical across memory presets with Kimi K3 in C",
 "summary": "Run the same prompt on a small and a large preset and compare the generated text.",
 "who": "A researcher or tester who needs evidence that a model gives the same answer regardless of how much memory the machine has.",
 "problem": "Changing memory settings can silently change results, which makes benchmarks and bug reports hard to trust.",
 "outcome": "Two runs with different presets print the same generated text, and only the timing lines differ.",
 "steps": [
  "Run the laptop preset command with --ids so no tokenizer is needed: ./bin/k3 ~/k3model --ids 1008,10484,318,15383,387 --trunk ~/k3trunk --preset laptop --gen 8 --incremental (inferred, check the README)",
  "./bin/k3 ~/k3model --trunk ~/k3trunk --preset server --tok ~/k3model --prompt \"def fibonacci(n):\" --gen 28 --incremental",
  "Save the generated text from each run.",
  "Diff the two outputs and confirm they match."
 ],
 "agent_prompt": "In the repo FareedKhan-dev/kimi-k3-in-c, run the same prompt with the laptop preset and the server preset, using --incremental. Expect two generated text blocks with timing lines. Verify that the generated text is byte-identical between the two runs.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 h 15 min (excludes the checkpoint download)",
 "basis": "readme",
 "caveat": "The README reports byte-identical output across machine sizes, but the server run needs a machine with far more memory and is only a timing comparison in practice.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "c",
 "requirements": [
  "A checkpoint directory of .safetensors shards (1.56 TB on disk for the released checkpoint)",
  "A packed trunk directory, created in a step the README excerpt does not show",
  "tiktoken.model and tokenizer_config.json in a directory, for text input",
  "A machine with a C toolchain for the portable C99 build (build steps are not in the excerpt)",
  "An HF_TOKEN environment variable if you use download-model.sh"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/fareedkhan-dev-kimi-k3-in-c/verify-identical-output-across-memory-presets/",
 "md": "https://dedupedai.com/use-cases/fareedkhan-dev-kimi-k3-in-c/verify-identical-output-across-memory-presets/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/fareedkhan-dev-kimi-k3-in-c--verify-identical-output-across-memory-presets.json",
 "api_version": "v1"
}