{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "p-e-w-heretic--fit-decensoring-into-limited-vram",
 "repo": "p-e-w/heretic",
 "repo_url": "https://github.com/p-e-w/heretic",
 "repo_slug": "p-e-w-heretic",
 "title": "Decensor a larger model on a small GPU with 4-bit quantization",
 "page_title": "How to decensor a larger model on a small GPU with 4-bit quantization with Heretic",
 "summary": "Turn on bitsandbytes 4-bit quantization so a model fits into less VRAM during the run.",
 "who": "A user with a consumer GPU who wants to process a model that would otherwise not fit in memory.",
 "problem": "Full-precision processing needs more VRAM than the user's card has.",
 "outcome": "A decensoring run completed with the model loaded in 4-bit form.",
 "steps": [
  "Run `pip install -U heretic-llm`.",
  "Run `heretic --help` to see the available command-line options and how to pass configuration.",
  "Copy `config.default.toml` from the repo and set the `quantization` option to `bnb_4bit`. (inferred, check the README)",
  "Run `heretic <model-id>` with the configuration file you edited, using the option form shown in `heretic --help`. (inferred, check the README)",
  "Watch the start of the run, where Heretic benchmarks the system to choose a batch size."
 ],
 "agent_prompt": "Install heretic-llm from the p-e-w/heretic repo and set the quantization option to bnb_4bit in a copy of config.default.toml. Then run Heretic on <model-id> using that configuration. Report whether the run completed, and verify that the log shows the bnb_4bit setting was applied.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 hour 30 minutes",
 "basis": "readme",
 "caveat": "The README says quantization can drastically reduce VRAM use, but it does not give exact memory figures, so test on your own hardware.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.10 or newer",
  "PyTorch 2.2 or newer, installed for your hardware",
  "A GPU with enough VRAM for the model you pick (the README cites an RTX 3090 and an RTX 5090)",
  "Access to the target model's files, such as a Hugging Face model ID"
 ],
 "risk": "dual-use",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "reverse-engineering",
   "notice": "The output is still a model with its safety alignment removed, so the same license and local-rule checks apply after quantized processing."
  }
 ],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/p-e-w-heretic/fit-decensoring-into-limited-vram/",
 "md": "https://dedupedai.com/use-cases/p-e-w-heretic/fit-decensoring-into-limited-vram/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/p-e-w-heretic--fit-decensoring-into-limited-vram.json",
 "api_version": "v1"
}