# MX3 on Intel N5105 SBC - illegal instruction

**URL:** <https://community.memryx.com/t/mx3-on-intel-n5105-sbc-illegal-instruction/171>\
**Category:** Technical Support\
**Created:** [March 4, 2026, 11:46pm UTC](https://community.memryx.com/t/mx3-on-intel-n5105-sbc-illegal-instruction/171 "2026-03-04T23:46:48Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![andrey](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.memryx.com/andrey/32/63_2.png) [@andrey](https://community.memryx.com/u/andrey)\
**Post date:** [March 4, 2026, 11:46pm UTC](https://community.memryx.com/t/mx3-on-intel-n5105-sbc-illegal-instruction/171/1 "2026-03-04T23:46:49Z")

</div>

Hi folks,

I’m setting up a Frigate instance on Odroid H3 + Debian 13. SDK install went smooth until the very last step - `mx_nc –version`. `mx_nc` crashes with illegal instruction and initial digging points to `vmovq` (in `neural_compiler`) that belongs to AVX/AVX2 instruction set. Odroid H3 is sporting Celeron N5105 (~2021) that only supports SSE4.2.

What are my choices here?

Do you guys need AVX?

Would it be too much trouble to recompile the SDK for SSE4 or make AVX dependency conditional?

Should I abandon H3? If MX3 worked with it, it would be such a good fit for Frigate…

Thanks!

---

<div class="post-metadata">

**Author:** ![abinila\_siva](https://avatars.discourse-cdn.com/v4/letter/a/c67d28/32.png) [@abinila\_siva](https://community.memryx.com/u/abinila_siva)\
**Post date:** [March 5, 2026, 9:00pm UTC](https://community.memryx.com/t/mx3-on-intel-n5105-sbc-illegal-instruction/171/2 "2026-03-05T21:00:21Z")

</div>

Hi Andrey,

Thanks for reaching out.

1. The **MemryX SDK** depends on several third-party libraries, such as **TensorFlow, TensorFlow Lite, and PyTorch** , that require **AVX support** on x86 CPUs. So, the prebuilt SDK packages currently expect an AVX-capable CPU.

2. **Frigate’s** default object detection pipeline also typically requires AVX on x86 CPUs. This has been discussed in the Frigate community here: [https://github.com/blakeblackshear/frigate/issues/14712](https://github.com/blakeblackshear/frigate/issues/14712 "https://github.com/blakeblackshear/frigate/issues/14712")

3. There is a **workaround** to use **MemryX** on systems **without AVX** by building the required runtime components manually and skipping AVX-dependent plugins.

- **First, build MXAccl and mxa\_manager from source:**  
[https://github.com/memryx/MxAccl](https://github.com/memryx/MxAccl "https://github.com/memryx/mxaccl")

- **Next, install the MemryX Python package:**  
[https://github.com/memryx/mx\_accl\_frigate](https://github.com/memryx/mx_accl_frigate "https://github.com/memryx/mx\_accl\_frigate")

- **Notes:**

Please follow the instructions in those repositories, and let us know if you run into any issues during setup — we’d be happy to help.

Thank you for your interest in using MemryX with Frigate.