The Serving Stack
Start hereCollectionsNewsletter
Sign in

gguf

1 post

QUANTIZATION · 11Q4BITSKK-QUANTMMIX4.0 NOMINAL → 4.9 REALBITS PER WEIGHT, QWEN3-8B Q4_K_M
quantizationggufllama-cpp

GGUF Quant Types Decoded: K-Quants and I-Quants

What Q4_K_M, IQ3_XXS, and the rest mean: the block layouts from llama.cpp's source, the real bits per weight of each file, and the weight error of each type on Qwen3-8B.

by The Serving Stack

Inference Notes

Once a week: what changed in serving AI models, and what it means if you build, run or pay for them, in about five minutes.

The Serving Stack

Inference Engineering, In Depth

Navigate

HomeStart hereCollectionsNewsletterAll articles

Collections

Inference EnginesHow an LLM Request Becomes TokensLLMs, ExplainedThe GPU for Inference EngineersQuantization in PracticeServing in Production

Links

RSS Feed

Legal

Privacy PolicyTerms of ServiceCookie Policy
© 2026 The Serving Stack. All rights reserved.