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.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
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.
import torch
before = torch.cuda.memory_allocated()
# Training step
optimizer.step()
after = torch.cuda.memory_allocated()
print(f"Memory used: {(after-before)/1e9:.2f}GB")
When to use vs alternatives
Use bitsandbytes when:
GPU memory limited (need to fit larger model)
Training with QLoRA (fine-tune 70B on single GPU)
Inference only (50-75% memory reduction)
Using HuggingFace Transformers
Acceptable 0-2% accuracy degradation
Use alternatives instead:
GPTQ/AWQ: Production serving (faster inference than bitsandbytes)
GGUF: CPU inference (llama.cpp)
FP8: H100 GPUs (hardware FP8 faster)
Full precision: Accuracy critical, memory not constrained
Common issues
Issue: CUDA error during loading
Install matching CUDA version:
# Check CUDA version
nvcc --version
# Install matching bitsandbytes
pip install bitsandbytes --no-cache-dir
Issue: Model loading slow
Use CPU offload for large models:
model = AutoModelForCausalLM.from_pretrained(
"model-name",
quantization_config=config,
device_map="auto",
max_memory={0: "20GB", "cpu": "30GB"} # Offload to CPU
)
Issue: Lower accuracy than expected
Try 8-bit instead of 4-bit:
config = BitsAndBytesConfig(load_in_8bit=True)
# 8-bit has <0.5% accuracy loss vs 1-2% for 4-bit
Or use NF4 with double quantization:
config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4", # Better than fp4
bnb_4bit_use_double_quant=True# Extra accuracy
)
Issue: OOM even with 4-bit
Enable CPU offload:
model = AutoModelForCausalLM.from_pretrained(
"model-name",
quantization_config=config,
device_map="auto",
offload_folder="offload", # Disk offload
offload_state_dict=True
)
Advanced topics
QLoRA training guide: See references/qlora-training.md for complete fine-tuning workflows, hyperparameter tuning, and multi-GPU training.
Quantization formats: See references/quantization-formats.md for INT8, NF4, FP4 comparison, double quantization, and custom quantization configs.
Memory optimization: See references/memory-optimization.md for CPU offloading strategies, gradient checkpointing, and memory profiling.
Hardware requirements
GPU: NVIDIA with compute capability 7.0+ (Turing, Ampere, Hopper)
Do not install alongside auto-gptq in the same environment. Both modify quantization kernels. Version mismatches cause CUDA errors. Use separate virtual environments.
