Agent skill · davila7
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
Reference it in any coding agent with:
@skills davila7/gptqAgent skill · davila7
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
Reference it in any coding agent with:
@skills davila7/gptq