# Loading models onto AMB82

**URL:** <https://forum.amebaiot.com/t/loading-models-onto-amb82/3303>\
**Category:** AI\
**Tags:** evb-amb82, rtl8735b\
**Created:** [September 3, 2024, 11:56am UTC](https://forum.amebaiot.com/t/loading-models-onto-amb82/3303 "2024-09-03T11:56:09Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![pchatty](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/pchatty/32/2187_2.png) [@pchatty](https://forum.amebaiot.com/u/pchatty)\
**Post date:** [September 3, 2024, 11:56am UTC](https://forum.amebaiot.com/t/loading-models-onto-amb82/3303/1 "2024-09-03T11:56:09Z")

</div>

Hi, I’m using AMB82-mini for a binary classification problem. I have models quantized using TF. I had been using Raspberry Pi but now am interested in migrating to a powerful MCU like said.

I see that the compatible format for models is .nb, which I am unaware of. The system expects me to upload my model on the AI Conversion Platform ( [Amebapro2 AI Convert Model – Realtek IoT/Wi-Fi MCU Solutions (amebaiot.com)](https://www.amebaiot.com/en/amebapro2-ai-convert-model/)) and wait for an email. Is there a more transparent way to get this done? I’d be happy to do this myself programmatically.

Or is there a way to use TFLite on AMB82-mini?

Regards,  
pchat

---

<div class="post-metadata">

**Author:** ![KaiFai\_Y](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/kaifai_y/32/2252_2.png) [@KaiFai\_Y](https://forum.amebaiot.com/u/KaiFai_Y)\
**Post date:** [September 9, 2024, 5:33am UTC](https://forum.amebaiot.com/t/loading-models-onto-amb82/3303/2 "2024-09-09T05:33:58Z")

</div>

Hi @pchatty,

Currently this was the only method for obtaining the .nb format. However, self-conversion may be implementation in the future.

Thank you

---

<div class="post-metadata">

**Author:** ![MJK](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/mjk/32/2487_2.png) [@MJK](https://forum.amebaiot.com/u/MJK)\
**Post date:** [April 6, 2025, 9:19am UTC](https://forum.amebaiot.com/t/loading-models-onto-amb82/3303/3 "2025-04-06T09:19:24Z")

</div>

have you tried it converting? mine takes so long

---

<div class="post-metadata">

**Author:** ![pchatty](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/pchatty/32/2187_2.png) [@pchatty](https://forum.amebaiot.com/u/pchatty)\
**Post date:** [April 7, 2025, 1:29am UTC](https://forum.amebaiot.com/t/loading-models-onto-amb82/3303/4 "2025-04-07T01:29:00Z")

</div>

Yeah, the conversion seems fine for me if the model is a custom CNN or something light basically. If I use a larger model (typically a transfer learning model), it takes forever and ends up failing at times.

PS I have given up on AMB82 and moved to other options that allow more control like ESP32 CAM, Portenta and Nicla Vision

PC

---

<div class="post-metadata">

**Author:** ![MJK](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/mjk/32/2487_2.png) [@MJK](https://forum.amebaiot.com/u/MJK)\
**Post date:** [April 7, 2025, 2:38am UTC](https://forum.amebaiot.com/t/loading-models-onto-amb82/3303/5 "2025-04-07T02:38:01Z")

</div>

about how long does it take to arrive in your email?

---

<div class="post-metadata">

**Author:** ![KevinKL](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.amebaiot.com/kevinkl/32/2632_2.png) [@KevinKL](https://forum.amebaiot.com/u/KevinKL)\
**Post date:** [April 24, 2025, 1:45am UTC](https://forum.amebaiot.com/t/loading-models-onto-amb82/3303/6 "2025-04-24T01:45:11Z")

</div>

Hello

If the server is working well, typically it will reach your email within minutes.

Thank you