inference/research
verifiedhigh · 0.90updated 2026-10-03

Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instruct

paper

Fields

id
sources/quant-gguf-kquant-study
URL
https://arxiv.org/abs/2601.14277
Publisher
arXiv
Kind
paper
Published
2026-01-11
Accessed
2026-10-03
notes
Kurt. Unified K-quant / legacy eval: WikiText-2 ppl + GSM8K/HSwag/IFEval/MMLU/TQA + CPU throughput. Only single-model study found.

Notes

Kurt. Unified K-quant / legacy eval: WikiText-2 ppl + GSM8K/HSwag/IFEval/MMLU/TQA + CPU throughput. Only single-model study found.

Cross-references

This record references no other records.