Bitsandbytes 8bit Nf4 Quantization

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 optimizers. Works with HuggingFace Transformers.

robertoatila Updated 9 repo stars
J.A.R.V.I.S. — Autonomous Cognitive Runtime

File contents

robertoatila/jarvis-skill-registry commit b074c58eb4

Frequently asked questions

npx get-skill add robertoatila/bitsandbytes-8bit-nf4-quantization-2