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.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
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.
