# Model compatibility for OpenMV Cam RT1062: .tflite formats and quantization (int8 vs float32)

**URL:** <https://forums.openmv.io/t/model-compatibility-for-openmv-cam-rt1062-tflite-formats-and-quantization-int8-vs-float32/11463>\
**Category:** OpenMV Boards\
**Tags:** tensorflow, tf, ml\
**Created:** [January 2, 2026, 8:42pm UTC](https://forums.openmv.io/t/model-compatibility-for-openmv-cam-rt1062-tflite-formats-and-quantization-int8-vs-float32/11463 "2026-01-02T20:42:58Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![joaop](https://avatars.discourse-cdn.com/v4/letter/j/b9e5f3/32.png) [@joaop](https://forums.openmv.io/u/joaop)\
**Post date:** [January 2, 2026, 8:42pm UTC](https://forums.openmv.io/t/model-compatibility-for-openmv-cam-rt1062-tflite-formats-and-quantization-int8-vs-float32/11463/1 "2026-01-02T20:42:58Z")

</div>

Hi everyone,

I am working with the OpenMV Cam RT1062 and I have a few questions regarding the deployment of neural networks on this specific hardware:

1. Does the RT1062 support only **.tflite** models, or is there support for other formats?

2. Regarding quantization: Does the model strictly need to be **fully quantized to int8** , or can the camera also run **float32** models efficiently?

3. If float32 is supported, is there a significant performance penalty compared to int8 on the i.MX RT1062?

I am currently training a character recognition model and want to ensure I’m exporting the best format for this board.

Thanks in advance for the help!

---

<div class="post-metadata">

**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\
**Post date:** [January 2, 2026, 8:55pm UTC](https://forums.openmv.io/t/model-compatibility-for-openmv-cam-rt1062-tflite-formats-and-quantization-int8-vs-float32/11463/2 "2026-01-02T20:55:27Z")

</div>

> Does the RT1062 support only **.tflite** models, or is there support for other formats?

Just tflite. Its because we use Googles TFLite runtime for Microcontrollers.Regarding quantization:

> Does the model strictly need to be **fully quantized to int8** , or can the camera also run **float32** models efficiently?

It needs to be mostly INT8. You can full float32 models, but, they will be much slower.

> If float32 is supported, is there a significant performance penalty compared to int8 on the i.MX RT1062?

Yes, it’s slower.