Transformers documentation


You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v4.41.3).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started


Half-Quadratic Quantization (HQQ) implements on-the-fly quantization via fast robust optimization. It doesn’t require calibration data and can be used to quantize any model.
Please refer to the official package for more details.

For installation, we recommend you use the following approach to get the latest version and build its corresponding CUDA kernels:

pip install hqq

To quantize a model, you need to create an HqqConfig. There are two ways of doing it:

from transformers import AutoModelForCausalLM, AutoTokenizer, HqqConfig

# Method 1: all linear layers will use the same quantization config
quant_config  = HqqConfig(nbits=8, group_size=64, quant_zero=False, quant_scale=False, axis=0) #axis=0 is used by default
# Method 2: each linear layer with the same tag will use a dedicated quantization config
q4_config = {'nbits':4, 'group_size':64, 'quant_zero':False, 'quant_scale':False}
q3_config = {'nbits':3, 'group_size':32, 'quant_zero':False, 'quant_scale':False}
quant_config  = HqqConfig(dynamic_config={

  'mlp.up_proj'  :q3_config,

The second approach is especially interesting for quantizing Mixture-of-Experts (MoEs) because the experts are less affected by lower quantization settings.

Then you simply quantize the model as follows

model = transformers.AutoModelForCausalLM.from_pretrained(

Optimized Runtime

HQQ supports various backends, including pure Pytorch and custom dequantization CUDA kernels. These backends are suitable for older gpus and peft/QLoRA training. For faster inference, HQQ supports 4-bit fused kernels (TorchAO and Marlin), reaching up to 200 tokens/sec on a single 4090. For more details on how to use the backends, please refer to

< > Update on GitHub