# Quantizing a Model

Each of the snpe-*framework*-to-dlc conversion tools convert
non-quantized models into a non-quantized DLC file. Quantizing
requires another step. The
[snpe-dlc-quantize](https://docs.qualcomm.com/doc/80-63442-2/topic/tools.html#snpe-dlc-quantize) tool
is used to quantize the model to one of supported fixed point
formats.

For example, the following command will convert an Inception v3
DLC file into a quantized Inception v3 DLC file.

snpe-dlc-quantize --input_dlc inception_v3.dlc --input_list image_file_list.txt
                      --output_dlc inception_v3_quantized.dlc
    Copy to clipboard

The image list specifies paths to raw image files used for
quantization. See
[snpe-dlc-quantize](https://docs.qualcomm.com/doc/80-63442-2/topic/tools.html#snpe-dlc-quantize) for
more details.

The tool requires the batch dimension of the DLC input file to
be set to 1 during model conversion. The batch dimension can be
changed to a different value for inference, by
[resizing](https://docs.qualcomm.com/doc/80-63442-2/topic/network_resize.html) the network during
initialization.

For details on the quantization algorithm, and information on
when to use a quantized model, see [Quantized vs Non-Quantized
Models](https://docs.qualcomm.com/doc/80-63442-2/topic/quantized_models.html).

Input data for quantization

To properly calculate the ranges for the quantization
parameters, a representative set of input data needs to be used
as input into
[snpe-dlc-quantize](https://docs.qualcomm.com/doc/80-63442-2/topic/tools.html#snpe-dlc-quantize).

Experimentation shows that providing 5-10 input data examples
in the input\_list for
[snpe-dlc-quantize](https://docs.qualcomm.com/doc/80-63442-2/topic/tools.html#snpe-dlc-quantize) is
usually sufficient, and definitely practical for quick
experiments. For more robust quantization results, we recommend
providing 50-100 examples of *representative* input data for
the given model use case, without using data from the training
set. The representative input data set ideally should include
all input data modalities which represent/produce all the
output types/classes of the model, preferably with several
input data examples per output type/class.

In [Supported Network Layers](https://docs.qualcomm.com/doc/80-63442-2/topic/network_layers.html), we have listed
the layers/ops that are guaranteed to be quantized successfully. For
other layers/ops no guarantees can be made.

Last Published: Oct 02, 2025

[Previous Topic
ONNX Model Conversion](https://docs.qualcomm.com/bundle/publicresource/80-63442-2/topics/model_conv_onnx.md) [Next Topic
Offline Graph Caching for DSP Runtime on HTP](https://docs.qualcomm.com/bundle/publicresource/80-63442-2/topics/offline_graph_caching.md)