Agent Skills: optimization-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.

ID: davila7/claude-code-templates/optimization-gptq

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill optimization-gptq

Skill Files

The files that make up optimization-gptq.

Download Skill

More agent skills