Hugging Face Transformers documentation: Bitsandbytes
repo
Fields
id
sources/qlab2-transformers-bnb-docPublisher
Hugging Face
Kind
repo
Accessed
2026-10-03
notes
BitsAndBytesConfig reference. Hardware support: NVIDIA CUDA 11.8-13.0, Intel XPU, Intel Gaudi HPU, CPU; min hardware Pascal for NF4/FP4 and Turing for LLM.int8(). Nested quantization saves an additional 0.4 bits/param. bnb_4bit_compute_dtype=torch.bfloat16 documented for dequantized matmul; bnb_4bit_quant_type is nf4 or fp4. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.
Notes
BitsAndBytesConfig reference. Hardware support: NVIDIA CUDA 11.8-13.0, Intel XPU, Intel Gaudi HPU, CPU; min hardware Pascal for NF4/FP4 and Turing for LLM.int8(). Nested quantization saves an additional 0.4 bits/param. bnb_4bit_compute_dtype=torch.bfloat16 documented for dequantized matmul; bnb_4bit_quant_type is nf4 or fp4. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.
Cross-references
This record references no other records.