Arm Learning Paths

ML

Understand KleidiAI SME2 matmul microkernels

C++ - KleidiAI - llama.cpp - SME2 - Android

06 Mar 2026 40 min

ML

Build, optimize, and deploy ML models with ONNX on Arm64 and mobile devices

Python - PyTorch - TensorFlow - ONNX - Android

03 Mar 2026 4 hrs

ML

Profile ONNX model performance with SME2 using KleidiAI and ONNX Runtime

C++ - ONNX Runtime - SME2 - Android - Linux

02 Mar 2026 40 min

ML

Profile ExecuTorch models with SME2 on Arm

ExecuTorch - Python - CMake - SME2 - macOS

02 Mar 2026 1 hr 30 min

ML

Measure LLM inference performance with KleidiAI and SME2 on Android

SME2 - C++ - llama.cpp - Android - Linux

02 Mar 2026 40 min

ML

Accelerate LiteRT Models on Android with KleidiAI and SME2

C - Python - SME2 - Android

02 Mar 2026 45 min

ML

Fine-tune PyTorch models on DGX Spark

Python - PyTorch - Docker - Hugging Face - Linux

28 Feb 2026 1 hr

ML

Deploy a Large Language Model (LLM) chatbot with llama.cpp using KleidiAI on Arm servers

LLM - Generative AI - Python - Demo - Hugging Face

24 Feb 2026 30 min

ML

Run vLLM inference with INT4 quantization on Arm servers

vLLM - LM Evaluation Harness - LLM - Generative AI - Python

23 Feb 2026 1 hr

ML

Optimize C++ performance with Profile-Guided Optimization and Google Benchmark

Google Benchmark - Runbook - Linux

23 Feb 2026 15 min

ML

Deploy DeepSeek-R1 on Arm Servers with llama.cpp

LLM - Generative AI - Python - Linux

23 Feb 2026 30 min

ML

Build a RAG application using Zilliz Cloud on Arm servers

Python - Generative AI - RAG - Hugging Face - Linux

23 Feb 2026 20 min

ML

Accelerate Whisper on Arm with Hugging Face Transformers

Python - Whisper - Demo - Hugging Face - Linux

23 Feb 2026 15 min

ML

Use Keras Core with TensorFlow, PyTorch, and JAX backends

Python - Keras - TensorFlow - PyTorch - JAX

23 Feb 2026 30 min

ML

Run Text Classification with ThirdAI on Arm servers

Python - ThirdAI - Linux

23 Feb 2026 10 min

ML

Run an LLM chatbot with rtp-llm on Arm-based servers

LLM - Generative AI - Python - Hugging Face - Linux

23 Feb 2026 30 min

ML

Run a Natural Language Processing (NLP) model from Hugging Face on Arm servers

Python - PyTorch - Hugging Face - Linux

23 Feb 2026 20 min

ML

Run a Large Language Model (LLM) chatbot with PyTorch using KleidiAI on Arm servers

LLM - Generative AI - Python - PyTorch - Hugging Face

23 Feb 2026 30 min

ML

Port Code to Arm Scalable Vector Extension (SVE)

SVE - NEON - armie - GCC - armclang

23 Feb 2026 30 min

ML

Measure and accelerate PyTorch Inference on Arm servers

Python - PyTorch - Linux

23 Feb 2026 20 min

ML

Deploy ModelScope FunASR Model on Arm Servers

ModelScope - FunASR - LLM - Generative AI - Python

23 Feb 2026 1 hr

ML

Deploy an AI Agent on Arm with llama.cpp and llama-cpp-agent using KleidiAI

Python - AWS Graviton - AI - Linux

23 Feb 2026 45 min

ML

Build and Run vLLM on Arm Servers

vLLM - LLM - Generative AI - Python - Hugging Face

23 Feb 2026 45 min

ML

Accelerate Natural Language Processing (NLP) models from Hugging Face on Arm servers

Python - PyTorch - Hugging Face - Linux

23 Feb 2026 20 min

ML

Run distributed inference with llama.cpp on Arm-based AWS Graviton4 instances

LLM - Generative AI - AWS - Linux

20 Feb 2026 30 min

ML

Measure Machine Learning Inference Performance on Arm servers

TensorFlow - Runbook - Linux

20 Feb 2026 20 min

ML

Deploy Phi-4-mini model with ONNX Runtime on Azure Cobalt 100

Python - ONNX Runtime - Linux

20 Feb 2026 30 min

ML

Deploy Arcee AFM-4.5B on Arm-based Google Cloud Axion with Llama.cpp

Google Cloud - Hugging Face - Python - Llama.cpp - Linux

20 Feb 2026 30 min

ML

Deploy Arcee AFM-4.5B on Arm-based AWS Graviton4 with Llama.cpp

AWS - Hugging Face - Python - Llama.cpp - Linux

20 Feb 2026 30 min

ML

Deploy a RAG-based Chatbot with llama-cpp-python using KleidiAI on Google Axion processors

Python - Streamlit - Google Axion - Demo - Hugging Face

20 Feb 2026 45 min

ML

Deploy a LLM-based Vision Chatbot with PyTorch and Hugging Face Transformers on Google Axion processors

Python - PyTorch - Streamlit - Google Axion - Linux

20 Feb 2026 45 min

ML

Quantize neural upscaling models with ExecuTorch

ExecuTorch - TorchAO - Vulkan - TOSA - NX

20 Feb 2026 1 hr

ML

Deploy TensorFlow on Google Cloud C4A (Arm-based Axion VMs)

TensorFlow - Python - Keras - Linux

20 Feb 2026 30 min

ML

Deploy SqueezeNet 1.0 INT8 model with ONNX Runtime on Azure Cobalt 100

Python - ONNX Runtime - Linux

20 Feb 2026 1 hr

ML

Fine-tuning neural graphics models with Model Gym

PyTorch - Jupyter Notebook - Vulkan - NX - Linux

10 Feb 2026 45 min

ML

Neural Super Sampling in Unreal Engine

Unreal Engine - Vulkan SDK - Visual Studio - NX - Windows

09 Feb 2026 30 min

ML

Get started with neural graphics using ML Extensions for Vulkan®

Vulkan - RenderDoc - NX - Windows

09 Feb 2026 30 min

ML

Create a ChatGPT voice bot on a Raspberry Pi

ChatGPT - Porcupine - Python - Linux

30 Jan 2026 1 hr

ML

Navigate Machine Learning development with Ethos-U processors

FVP - Arm Virtual Hardware - GCC - Arm Compiler for Embedded - MPS3

30 Jan 2026 10 min

ML

Deploy PaddlePaddle on Arm Cortex-M with Arm Virtual Hardware

Arm Virtual Hardware - GCC - Paddle - TVMC - Baremetal

30 Jan 2026 30 min

ML

Build and run an image classification NN model on an STM32L4 Discovery board

TensorFlow - STM32 - Baremetal

30 Jan 2026 1 hr

ML

Build and run a letter recognition NN model on an STM32L4 Discovery board

TensorFlow - STM32 - Baremetal

30 Jan 2026 1 hr

ML

Run ERNIE-4.5 Mixture of Experts model on Armv9 with llama.cpp

Python - CPP - Bash - llama.cpp - Linux

16 Jan 2026 1 hr

ML

Accelerate Generative AI workloads using KleidiAI

CPP - Generative AI - NEON - Runbook - Linux

14 Jan 2026 1 hr

ML

Build a Privacy-First LLM Smart Home on Raspberry Pi 5

Python - Ollama - gpiozero - lgpio - FastAPI

14 Jan 2026 45 min

ML

Profile the Performance of AI and ML Mobile Applications on Arm

Android Studio - LiteRT - Hugging Face - Android - Linux

14 Jan 2026 1 hr

ML

Vision LLM inference on Android with KleidiAI and MNN

Android Studio - KleidiAI - Android

14 Jan 2026 30 min

ML

Build an Android chat app with Llama, KleidiAI, ExecuTorch, and XNNPACK

Java - CPP - Python - Hugging Face - ExecuTorch

07 Jan 2026 1 hr

ML

Run Phi-3 on Windows on Arm using ONNX Runtime

Visual Studio - CPP - Python - Git - CMake

06 Jan 2026 1 hr

ML

Profile llama.cpp performance with Arm Streamline and KleidiAI LLM kernels

Arm Streamline - CPP - llama.cpp - Profiling - Linux

06 Jan 2026 1 hr

ML

Build an Android chat application with ONNX Runtime API

Kotlin - CPP - ONNX Runtime - Android - Hugging Face

06 Jan 2026 1 hr

ML

Run a Computer Vision Model on a Himax Microcontroller

Himax SDK - Python - Hugging Face - Linux - macOS

19 Dec 2025 1 hr 30 min

ML

Run a local LLM chatbot on a Raspberry Pi 5

LLM - Generative AI - Raspberry Pi - Python - Hugging Face

19 Dec 2025 30 min

ML

Benchmark a KleidiAI micro-kernel in ExecuTorch

Python - ExecuTorch - XNNPACK - KleidiAI - Linux

18 Dec 2025 30 min

ML

Unlock quantized LLM performance on Arm-based NVIDIA DGX Spark

Python - C - Bash - llama.cpp - Linux

18 Dec 2025 1 hr

ML

Learn how to run AI on Edge devices using Arduino Nano RP2040

Edge Impulse - tinyML - Edge AI - Arduino - Baremetal

18 Dec 2025 1 hr 30 min

ML

Build a RAG pipeline on Arm-based NVIDIA DGX Spark

Python - llama.cpp - Hugging Face - Linux

18 Dec 2025 1 hr

ML

Deploy an MCP Server on Raspberry Pi 5 for AI Agent Interaction using OpenAI SDK

Python - AI - Raspberry Pi - MCP - Linux

18 Dec 2025 30 min

ML

Create and train a PyTorch model for digit classification using the MNIST dataset

Android Studio - Visual Studio Code - Windows - Linux - macOS

18 Dec 2025 2 hrs 40 min

ML

Build and run Arm Total Solutions for IoT

Arm Virtual Hardware - FVP - Arm Compiler for Embedded - Baremetal - RTOS

10 Dec 2025 30 min

ML

Build a Hands-Free Selfie Android Application with MediaPipe

Android Studio - Kotlin - MediaPipe - Android

26 Nov 2025 2 hrs

ML

Visualize Ethos-U NPU performance with ExecuTorch on Arm FVPs

Arm Virtual Hardware - FVP - Python - PyTorch - ExecuTorch

11 Nov 2025 2 hrs

ML

Get started with object detection using a Jetson Orin Nano

DetectNet - TensorRT - Docker - Linux

11 Nov 2025 1 hr

ML

Detect faces with OpenCV on Android Devices

Android - Android Studio - Kotlin - Windows - macOS

11 Nov 2025 30 min

ML

Introduction to TinyML on Arm using PyTorch and ExecuTorch

Arm Virtual Hardware - FVP - Python - PyTorch - ExecuTorch

08 Nov 2025 40 min

ML

Run Llama 3 on a Raspberry Pi 5 using ExecuTorch

LLM - Generative AI - Raspberry Pi - Hugging Face - ExecuTorch

05 Nov 2025 1 hr

ML

Edge AI on Arm: PyTorch and ExecuTorch rock-paper-scissors

tinyML - Computer Vision - Edge AI - CNN - PyTorch

02 Oct 2025 1 hr

ML

Build and run the Arm Machine Learning Evaluation Kit examples

Arm Virtual Hardware - FVP - GCC - Arm Compiler for Embedded - Baremetal

05 Sep 2025 30 min

ML

LLM inference on Android with KleidiAI, MediaPipe, and XNNPACK

Java - MediaPipe - Android SDK - Android NDK - Bazel

02 Jun 2025 1 hr

Tag: ML

Filter

Understand KleidiAI SME2 matmul microkernels

Build, optimize, and deploy ML models with ONNX on Arm64 and mobile devices

Profile ONNX model performance with SME2 using KleidiAI and ONNX Runtime

Profile ExecuTorch models with SME2 on Arm

Measure LLM inference performance with KleidiAI and SME2 on Android

Accelerate LiteRT Models on Android with KleidiAI and SME2

Fine-tune PyTorch models on DGX Spark

Deploy a Large Language Model (LLM) chatbot with llama.cpp using KleidiAI on Arm servers

Run vLLM inference with INT4 quantization on Arm servers

Optimize C++ performance with Profile-Guided Optimization and Google Benchmark

Deploy DeepSeek-R1 on Arm Servers with llama.cpp

Build a RAG application using Zilliz Cloud on Arm servers

Accelerate Whisper on Arm with Hugging Face Transformers

Use Keras Core with TensorFlow, PyTorch, and JAX backends

Run Text Classification with ThirdAI on Arm servers

Run an LLM chatbot with rtp-llm on Arm-based servers

Run a Natural Language Processing (NLP) model from Hugging Face on Arm servers

Run a Large Language Model (LLM) chatbot with PyTorch using KleidiAI on Arm servers

Port Code to Arm Scalable Vector Extension (SVE)

Measure and accelerate PyTorch Inference on Arm servers

Deploy ModelScope FunASR Model on Arm Servers

Deploy an AI Agent on Arm with llama.cpp and llama-cpp-agent using KleidiAI

Build and Run vLLM on Arm Servers

Accelerate Natural Language Processing (NLP) models from Hugging Face on Arm servers

Run distributed inference with llama.cpp on Arm-based AWS Graviton4 instances

Measure Machine Learning Inference Performance on Arm servers

Deploy Phi-4-mini model with ONNX Runtime on Azure Cobalt 100

Deploy Arcee AFM-4.5B on Arm-based Google Cloud Axion with Llama.cpp

Deploy Arcee AFM-4.5B on Arm-based AWS Graviton4 with Llama.cpp

Deploy a RAG-based Chatbot with llama-cpp-python using KleidiAI on Google Axion processors

Deploy a LLM-based Vision Chatbot with PyTorch and Hugging Face Transformers on Google Axion processors

Quantize neural upscaling models with ExecuTorch

Deploy TensorFlow on Google Cloud C4A (Arm-based Axion VMs)

Deploy SqueezeNet 1.0 INT8 model with ONNX Runtime on Azure Cobalt 100

Fine-tuning neural graphics models with Model Gym

Neural Super Sampling in Unreal Engine

Get started with neural graphics using ML Extensions for Vulkan®

Create a ChatGPT voice bot on a Raspberry Pi

Navigate Machine Learning development with Ethos-U processors

Deploy PaddlePaddle on Arm Cortex-M with Arm Virtual Hardware

Build and run an image classification NN model on an STM32L4 Discovery board

Build and run a letter recognition NN model on an STM32L4 Discovery board

Run ERNIE-4.5 Mixture of Experts model on Armv9 with llama.cpp

Accelerate Generative AI workloads using KleidiAI

Build a Privacy-First LLM Smart Home on Raspberry Pi 5

Profile the Performance of AI and ML Mobile Applications on Arm

Vision LLM inference on Android with KleidiAI and MNN

Build an Android chat app with Llama, KleidiAI, ExecuTorch, and XNNPACK

Run Phi-3 on Windows on Arm using ONNX Runtime

Profile llama.cpp performance with Arm Streamline and KleidiAI LLM kernels

Build an Android chat application with ONNX Runtime API

Run a Computer Vision Model on a Himax Microcontroller

Run a local LLM chatbot on a Raspberry Pi 5

Benchmark a KleidiAI micro-kernel in ExecuTorch

Unlock quantized LLM performance on Arm-based NVIDIA DGX Spark

Learn how to run AI on Edge devices using Arduino Nano RP2040

Build a RAG pipeline on Arm-based NVIDIA DGX Spark

Deploy an MCP Server on Raspberry Pi 5 for AI Agent Interaction using OpenAI SDK

Create and train a PyTorch model for digit classification using the MNIST dataset

Build and run Arm Total Solutions for IoT

Build a Hands-Free Selfie Android Application with MediaPipe

Visualize Ethos-U NPU performance with ExecuTorch on Arm FVPs

Get started with object detection using a Jetson Orin Nano

Detect faces with OpenCV on Android Devices

Introduction to TinyML on Arm using PyTorch and ExecuTorch

Run Llama 3 on a Raspberry Pi 5 using ExecuTorch

Edge AI on Arm: PyTorch and ExecuTorch rock-paper-scissors

Build and run the Arm Machine Learning Evaluation Kit examples

LLM inference on Android with KleidiAI, MediaPipe, and XNNPACK