Agent skill · zechenzhangagi

quantizing-models-bitsandbytes

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want

Reference it in any coding agent with:

@skills zechenzhangagi/quantizing-models-bitsandbytes

Browse the @skills marketplace