{
  "abstract": "Measurements of how much compression can be added on top of the KV-cache formats (F16, Q8_0, Q4_0) and weight formats (BF16, Q8_0, Q4_K_M) used by llama.cpp, on one RTX 3090. A measurement study with mostly negative results; no new method is proposed. Includes the paper, all measurement records (R1-R87), llama.cpp patches, scripts and result summaries. All speed windows were shared with desktop applications; server-GPU rows are analytic projections.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "NeoXider"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b2kcws4p0xdt4.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23578725",
  "fulltext_url": null,
  "id": "b2kcws4p0xdt4",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23578725",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b2kcws4p0xdt4.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T12:20:19Z",
      "native_id": "23578725",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23578725"
    }
  ],
  "subjects": [],
  "title": "LLM compression measurements: lossless and lossy compression on top of existing KV-cache and weight formats (RTX 3090, llama.cpp)",
  "title_text": "LLM compression measurements: lossless and lossy compression on top of existing KV-cache and weight formats (RTX 3090, llama.cpp)",
  "type": "preprint",
  "updated_at": "2026-11-05T12:20:19Z",
  "url": "https://research.draconitic.com/paper/b2kcws4p0xdt4",
  "venue": "Zenodo",
  "versions": []
}