transformers/docs/source/en/quantization/overview.md

Quantization

Quantization techniques focus on representing data with less information while also trying to not lose too much accuracy. This often means converting a data type to represent the same information with fewer bits. For example, if your model weights are stored as 32-bit floating points and they're quantized to 16-bit floating points, this halves the model size which makes it easier to store and reduces memory-usage. Lower precision can also speedup inference because it takes less time to perform calculations with fewer bits.

Interested in adding a new quantization method to Transformers? Read the HfQuantizer guide to learn how!

If you are new to the quantization field, we recommend you to check out these beginner-friendly courses about quantization in collaboration with DeepLearning.AI:

• Quantization Fundamentals with Hugging Face
• Quantization in Depth

When to use what?

The community has developed many quantization methods for various use cases. With Transformers, you can run any of these integrated methods depending on your use case because each method has their own pros and cons.

For example, some quantization methods require calibrating the model with a dataset for more accurate and "extreme" compression (up to 1-2 bits quantization), while other methods work out of the box with on-the-fly quantization.

Another parameter to consider is compatibility with your target device. Do you want to quantize on a CPU, GPU, or Apple silicon?

In short, supporting a wide range of quantization methods allows you to pick the best quantization method for your specific use case.

Use the table below to help you decide which quantization method to use.

Quantization Method	On the fly quantization	CPU	CUDA GPU	ROCm GPU	Metal (Apple Silicon)	Intel GPU	Torch compile()	Bits	PEFT Fine Tuning	Serializable with 🤗Transformers	🤗Transformers Support	Link to library
AQLM	🔴	🟢	🟢	🔴	🔴	🔴	🟢	1/2	🟢	🟢	🟢	https://github.com/Vahe1994/AQLM
AWQ	🔴	🟢	🟢	🟢	🔴	🟢	?	4	🟢	🟢	🟢	https://github.com/casper-hansen/AutoAWQ
bitsandbytes	🟢	🟡 1	🟢	🟡 1	🔴 2	🟡 1	🔴 1	4/8	🟢	🟢	🟢	https://github.com/bitsandbytes-foundation/bitsandbytes
compressed-tensors	🔴	🟢	🟢	🟢	🔴	🔴	🔴	1/8	🟢	🟢	🟢	https://github.com/neuralmagic/compressed-tensors
EETQ	🟢	🔴	🟢	🔴	🔴	🔴	?	8	🟢	🟢	🟢	https://github.com/NetEase-FuXi/EETQ
GGUF / GGML (llama.cpp)	🟢	🟢	🟢	🔴	🟢	🔴	🔴	1/8	🔴	See Notes	See Notes	https://github.com/ggerganov/llama.cpp
GPTQModel	🔴	🟢 3	🟢	🟢	🟢	🟢 4	🔴	2/3/4/8	🟢	🟢	🟢	https://github.com/ModelCloud/GPTQModel
AutoGPTQ	🔴	🔴	🟢	🟢	🔴	🔴	🔴	2/3/4/8	🟢	🟢	🟢	https://github.com/AutoGPTQ/AutoGPTQ
HIGGS	🟢	🔴	🟢	🔴	🔴	🔴	🟢	2/4	🔴	🟢	🟢	https://github.com/HanGuo97/flute
HQQ	🟢	🟢	🟢	🔴	🔴	🔴	🟢	1/8	🟢	🔴	🟢	https://github.com/mobiusml/hqq/
optimum-quanto	🟢	🟢	🟢	🔴	🟢	🔴	🟢	2/4/8	🔴	🔴	🟢	https://github.com/huggingface/optimum-quanto
FBGEMM_FP8	🟢	🔴	🟢	🔴	🔴	🔴	🔴	8	🔴	🟢	🟢	https://github.com/pytorch/FBGEMM
torchao	🟢	🟢	🟢	🔴	🟡 5	🔴		4/8		🟢🔴	🟢	https://github.com/pytorch/ao
VPTQ	🔴	🔴	🟢	🟡	🔴	🔴	🟢	1/8	🔴	🟢	🟢	https://github.com/microsoft/VPTQ
SpQR	🔴	🔴	🟢	🔴	🔴	🔴	🟢	3	🔴	🟢	🟢	https://github.com/Vahe1994/SpQR/
FINEGRAINED_FP8	🟢	🔴	🟢	🔴	🔴	🔴	🔴	8	🔴	🟢	🟢

1: bitsandbytes is being refactored to support multiple backends beyond CUDA. Currently, ROCm (AMD GPU) and Intel CPU implementations are mature, with Intel XPU in progress and Apple Silicon support expected by Q4/Q1. For installation instructions and the latest backend updates, visit this link. Check out these docs for more details and feedback links.

2: bitsandbytes is seeking contributors to help develop and lead the Apple Silicon backend. Interested? Contact them directly via their repo. Stipends may be available through sponsorships.

3: GPTQModel[CPU] supports 4-bit via IPEX on Intel/AMD and full bit range via Torch on Intel/AMD/Apple Silicon.

4: GPTQModel[Intel GPU] via IPEX only supports 4-bit for Intel Datacenter Max/Arc GPUs.

5: torchao only supports int4 weight on Metal (Apple Silicon).