# qtimlsnpe
Source: [https://docs.qualcomm.com/doc/80-70014-50/topic/qtimlsnpe.html](https://docs.qualcomm.com/doc/80-70014-50/topic/qtimlsnpe.html)
The qtimlsnpe plugin exposes the Qualcomm^®^ Neural Processing SDK
capabilities (load and execute the models).
It accepts a tensor prepared by pre-processing elements such as qtimlvconverter and
produces output tensor that can be parsed by postprocessing plug-ins such as
qtimlvclassification, qtimlvdetection, qtimlvsegmentation, and qtimlvpose.
This plugin does the following:
- Accepts a tensor prepared by the preprocessing elements such as
qtimlvconverter.
- Produces the output tensor that can be parsed by postprocessing plugins such as
qtimlvclassification, qtimlvdetection, qtimlvsegmentation, and qtimlvpose.
- Uses the Qualcomm Neural Processing SDK library.
- Uses the ION/DMA buffers allocated by the GstMLBufferPool custom buffer pool class
through IOCTL commands to the kernel.
The model and delegate usage is as follows:
- To use a model, provide the absolute path of the model through the model
property.
For some models, you may need to set the additional layers
property.
After it's loaded, the model file provides the input and output
capabilities:
- Number of tensors
- Dimensions
- Type
- If a delegate is not specified, the plugin executes the model operations on
CPU.
- To select a different delegate, set the delegate property accordingly. For more
information, see the [Table : Element properties of qtimlsnpe](https://docs.qualcomm.com/doc/80-70014-50/topic/qtimlsnpe.html#qtimlsnpe__table_ids_q34_myb) .
Figure : Tensor mode qtimlsnpe architecture
## Inheritance chain
[GObject](https://docs.gtk.org/gobject/) → [GstObject](https://gstreamer.freedesktop.org/documentation/gstreamer/gstobject.html?gi-language=c) → [GstElement](https://gstreamer.freedesktop.org/documentation/gstreamer/gstelement.html?gi-language=c) → [GstBaseTransform](https://gstreamer.freedesktop.org/documentation/base/gstbasetransform.html?gi-language=c) → GstMLSnpe
The following tables provide information on pad templates and element properties of
qtimlsnpe. For use cases, see [Qualcomm Neural Processing SDK use cases](https://docs.qualcomm.com/doc/80-70014-50/topic/qualcomm-neural-processing-sdk-use-cases.html).
## Pad configuration
| Pad Name | Capabilities | Capabilities | Capabilities |
| --- | --- | --- | --- |
| SINK template: 'sink'
- Availability: Always
- Direction: sink
| neural-network/tensors | type: | { (string)UINT8, (string)INT32, (string)FLOAT32 } |
| SRC template: 'src'
- Availability: Always
- Direction: source
| neural-network/tensors | type: | { (string)UINT8, (string)INT32, (string)FLOAT32 } |
## Element configuration
Table : Element properties of qtimlsnpe
| Property | Description |
| --- | --- |
| name | The name of the object
- flags: readable, writable
- String. Default: "mlsnpe0"
|
| parent | The parent of the object
- flags: readable, writable
- Object of type "GstObject"
|
| model | Model file name
- flags: readable, writable
- String. Default: null
|
| delegate | Delegate the graph execution to another executor
- flags: readable, writable
- Enum "GstMLSnpeDelegate" Default: 0, "none"
- (0): none - No delegate, CPU is used for all
operations
- (1): dsp - Run the processing on the Hexagon
DSP
- (2): gpu - Run the processing on the Adreno
GPU
- (3): aip - Run the processing on Snapdragon AIX +
HVX
|
| layers | List of output layers. Should be set if model has more than one
output
- flags: readable, writable
- GstValueArray of GValues of type "gchararray"
|
**Parent Topic:** [Qualcomm GST plugins](https://docs.qualcomm.com/doc/80-70014-50/topic/qim-sdk-plugins.html)
Last Published: Oct 27, 2025
[Previous Topic
Waylandsink](https://docs.qualcomm.com/bundle/publicresource/80-70014-50/topics/waylandsink.md) [Next Topic
qtimltflite](https://docs.qualcomm.com/bundle/publicresource/80-70014-50/topics/qtimltflite.md)