# Unable to Load Model on Genio 510 NPU with Python **URL:** \ **Category:** NeuroPilot - Analytical AI\ **Tags:** Genio-510, Question\ **Created:** [October 10, 2025, 1:48pm UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174 "2025-10-10T13:48:58Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Kunal\_Kalkotwar](https://avatars.discourse-cdn.com/v4/letter/k/9fc29f/32.png) [@Kunal\_Kalkotwar](https://genio-community.mediatek.com/u/Kunal_Kalkotwar)\ **Post date:** [October 10, 2025, 1:48pm UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174/1 "2025-10-10T13:48:58Z")
1. I am trying to run a TensorFlow Lite model on the Genio 510 EVK using the NPU for hardware acceleration. I am using `tflite_runtime` and attempting to load the Neuron delegate as follows: from tflite\_runtime.interpreter import Interpreter, load\_delegate delegate = load\_delegate(“/usr/lib/libneuron\_stable\_delegate.so”) Attempted with both CPU and delegate, delegate always fails Questions: How do I properly load a TensorFlow Lite model on the Genio 510 NPU? Do I need a MediaTek Neuron-patched `tflite_runtime`? If yes, how can I obtain it? Are there any example recipes or steps for integrating Neuron SDK with Yocto for Python inference? Any guidance, example code, or documentation references would be greatly appreciated. Thank you! ---
**Author:** ![Andres\_Campos](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/andres_campos/32/162_2.png) [@Andres\_Campos](https://genio-community.mediatek.com/u/Andres_Campos)\ **Post date:** [October 10, 2025, 5:14pm UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174/2 "2025-10-10T17:14:39Z")
Hello @Kunal_Kalkotwar , I believe you might find these links helpful: 1. [Official MediaTek Tao Tutorials](https://mediatek.gitlab.io/genio/doc/tao/tutorials/tao_tutorial_1.html#demo-example) 2. [MediaTek Tao Demos Source Code](https://gitlab.com/mediatek/aiot/rity/genio-tao-demos) On second link, you will be able to find instructions to enable the required libraries on your custom Yocto image for the custom tflite packages to be installed. Also, you can base on the [Action Recognition Demo](https://gitlab.com/mediatek/aiot/rity/genio-tao-demos/-/blob/main/Action_Recognition/action_recognition.py?ref_type=heads) for a sample Python implementation. Hope that helps. Please do not hesitate to reach out if you need further support, we would love to help. best regards, Andres Embedded Software Engineer at ProventusNova > **[Get Expert MediaTek Genio Support - Proventus Nova](https://proventusnova.com/get-expert-mediatek-genio-support/)** > > Book a free call now and get expert project consultation and a custom development plan within 2 business days. ---
**Author:** ![Kunal\_Kalkotwar](https://avatars.discourse-cdn.com/v4/letter/k/9fc29f/32.png) [@Kunal\_Kalkotwar](https://genio-community.mediatek.com/u/Kunal_Kalkotwar)\ **Post date:** [October 13, 2025, 11:09am UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174/3 "2025-10-13T11:09:44Z")
I’m not using a custom Yocto build; I’m working with the pre-built image provided for the MediaTek Genio 510 EVK. Please share the steps applicable for this setup. ---
**Author:** ![Andres\_Campos](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/andres_campos/32/162_2.png) [@Andres\_Campos](https://genio-community.mediatek.com/u/Andres_Campos)\ **Post date:** [October 13, 2025, 3:38pm UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174/4 "2025-10-13T15:38:49Z")
Hello @Kunal_Kalkotwar, Thanks for sharing that detail! May I ask why are you not using a custom Yocto image ? I am just curious since that is very common across our most successful clients. And I don’t think I have an example with the pre-built image, however I can try to put something together for you during the day. best regards, Andrew Embedded Software Engineer at ProventusNova > **[Get Expert NVIDIA Jetson Support - Proventus Nova](https://proventusnova.com/get-expert-nvidia-jetson-support/)** > > Home Expertise & Work Our Expertise Case Studies Blog Pricing Contact Book NVIDIA Jetson Consultation Call Get Expert NVIDIA Jetson Support Book a free call now and get expert project consultation and a custom development plan within 2 business... ---
**Author:** ![Suyash\_Narain](https://avatars.discourse-cdn.com/v4/letter/s/65b543/32.png) [@Suyash\_Narain](https://genio-community.mediatek.com/u/Suyash_Narain)\ **Post date:** [November 11, 2025, 6:04pm UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174/6 "2025-11-11T18:04:01Z")
Hi @Kunal_Kalkotwar Python API is currently not supported with NPU delegate. This is a TF restriction since our delegate is based on TF stable delegate API which only has C++ API. Python API development work is currently under progress. You should be able to use this C++ API [snippet](https://mediatek.gitlab.io/genio/doc/tao/npu_acceleration.html#code-snippet) to integrate your C++ application with NPU delegate. ---
**Author:** ![Kunal\_Kalkotwar](https://avatars.discourse-cdn.com/v4/letter/k/9fc29f/32.png) [@Kunal\_Kalkotwar](https://genio-community.mediatek.com/u/Kunal_Kalkotwar)\ **Post date:** [November 14, 2025, 6:33am UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174/7 "2025-11-14T06:33:49Z")
Thanks for replying I have compiled whisper models encoder in .dla format using mtk\_converter how can i deploy it on board. I am trying to give continuous audio to the model (dla) how can i achieve it. ---
**Author:** ![joying.kuo](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/joying.kuo/32/167_2.png) [@joying.kuo](https://genio-community.mediatek.com/u/joying.kuo)\ **Post date:** [June 9, 2026, 6:33am UTC](https://genio-community.mediatek.com/t/unable-to-load-model-on-genio-510-npu-with-python/1174/8 "2026-06-09T06:33:02Z")
Hi @Kunal_Kalkotwar , For now we haven’t yet provided the ASR demo solution for the dla inference. It’s expected to be supported by 2026 Q3 end. We will update the status on the forum announcement. Thanks for the inquiry:)