GPTQ
GPTQ is a library in our research taxonomy.
Related papers
- HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning
- What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
- Calibrating Beyond English: Language Diversity for Better Quantized Multilingual LLM
- Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model
- Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment