Baran Başaran·Dec 13, 2025Nedir Bu Quantizaton?Sayısal veri türleri: LLM’in içindeki her bir bireysel sayısal değeri temsil etmek için kullanılan bit sayısını ve formatını belirtir.
Dineshkumar Anandan·Oct 15, 2025The Quantum Leap: Making AI Models Lightning Fast with GPTQ and AWQ QuantizationThe Problem: When Your GPU Can’t Keep Up
Rajesh Kumar·Sep 24, 2025Making LLMs Smaller: The Story of GPTQTraditional LLMs such as GPT or Gemini 2.5 pro contains billions of paramaters. As the number of parameters increases, demand for memory…
Nikulsinh Rajput·Sep 18, 2025Quantization Without Tears: QLoRA vs AWQ vs GPTQCut VRAM, keep quality. A plain-English guide with working code and trade-offs that actually matter.
QuarkAndCode·Sep 15, 2025LLM Quantization for Inference: Common Pitfalls & Proven FixesMaster LLM quantization for inference: fix accuracy loss, activation spikes, and slow kernels. Learn when to use INT8/INT4, SmoothQuant…
Arun M·Jun 21, 2025Fine-tuning GPTQ Quantized Vision Language Models with LoRA.How to use Hugging Face’s Transformers Reinforcement Learning (TRL) library to finetune a 4-bit GPTQ quantized model using LoRA techniques.
Arun M·Jun 3, 2025Quantizing Qwen2-VL Models with GPTQModel and Running Efficient Inference with vLLMMaking vision-language models more accessible through 4-bit quantization
Doil Kim·May 13, 2025Speeding Up Large Language Models: A Deep Dive into GPTQ and AWQ QuantizationA Practical Guide to Reducing Model Size Without Sacrificing Performance
InData Science CollectivebyAnvee Naik·Feb 24, 2025Making LLMs Lighter: A deep dive into LLM quantization with CodeUnderstand how LLM quantization methods such as LLM.int8() and GPTQ worksA response icon1A response icon1
