Verified record · from the answer index
quantizing-models-bitsandbytes
skilltested · static-verifiedscore 49/100signed passport ✓924 uses
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 faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimiz
Declared tools (1)
quantizing-models-bitsandbytes
skill:orchestra-research/ai-research-skills/quantizing-models-bitsandbytes · published by orchestra-research · source repository