{"ok":true,"entity":{"slug":"bitsandbytes","entityType":"product","name":"bitsandbytes","officialName":"bitsandbytes","canonicalName":"bitsandbytes","displayName":"bitsandbytes","category":"量子化ライブラリ","shortDescription":"PyTorch向けのk-bit量子化ライブラリ。LLM.int8()やQLoRA（4-bit量子化）等の手法を実装し、少ないメモリでの大規模モデル推論・学習を可能にする。Hugging Face Transformersと標準的に統合されている。","alias":["bnb"],"searchKeywords":["量子化","LLM.int8","QLoRA","メモリ削減"],"website":"https://github.com/bitsandbytes-foundation/bitsandbytes","parentEntity":null,"primaryCluster":"ai-open-model","secondaryClusters":["ai-infrastructure"],"id":"bitsandbytes","verificationStatus":"draft","updatedAt":"2026-07-20T02:14:59.356Z"},"referenceIndex":["P-01-001","P-02-001","P-04-001"]}