home/categories/machine-learning/orchestra-research-ai-research-skills-10-optimization-gptq-skill-md
machine-learningdata-ai
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
maintainer
Orchestra-Research
Atualizado 11/20/2025
Estrelas
6563
Forks
515
quick start
Installation and usage
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Instalação
$ install --globalskills.sh
Uso
Depois de instalar, você pode usar esta skill executando o seguinte comando no terminal:
skills use gptq