Skip to content
codema.
  • AI
  • Tech
  • Finance
  • Resources
  • Newsletter
ENFR
Subscribe
Home/quantization
Tag

quantization

  • Build Guides

    Q4_K_M vs Q6_K vs FP8: the quality you lose and what fits your GPU

    BF16, FP8, MXFP8, NVFP4, INT4 and a dozen GGUF flavours, compared. What published benchmarks say about quality loss, and how to pick the file for your GPU or Mac.

    October 23, 20268 min readDerrick K.
codema.

The publisher for AI, tech and finance-tech.

Publication
  • News
  • Build Guides
  • Tools
  • Skills & Prompts
  • Opinion
  • Newsletter
  • Tech
  • Finance
  • Resources
  • Today in AI
  • How we write
  • Editorial standards & corrections
  • codema.ai/links
  • AI (RSS)
  • Tech (RSS)
  • Finance (RSS)
  • Privacy choices
  • Search
  • RSS
  • Today in AI (RSS)
Legal
  • Privacy Policy
  • Terms of Use
  • Disclaimer
  • Contact
  • Privacy request
© Codema. All rights reserved.codema.ai

Codema uses cookies only after you choose. Necessary cookies keep the site working. Analytics and advertising stay off until you opt in.

HomeAITechFinanceResources