# Tag: AI

## Filter

### Categories
- Automotive
- Embedded and Microcontrollers
- Laptops and Desktops
- Mobile, Graphics, and Gaming
- Servers and Cloud Computing

## Learning paths

- [Accelerate Generative AI workloads using KleidiAI](https://learn.arm.com/learning-paths/cross-platform/kleidiai-explainer/)
- [Run vLLM inference with INT4 quantization on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/vllm-acceleration/)
- [Fine-tune PyTorch models on DGX Spark](https://learn.arm.com/learning-paths/laptops-and-desktops/pytorch-finetuning-on-spark/)
- [Understand KleidiAI SME2 matmul microkernels](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/kai_sme2_matmul_ukernel_explained/)
- [Export and quantize SmolVLA for ONNX Runtime on Arm](https://learn.arm.com/learning-paths/cross-platform/smolvla-onnx-conversion/)
- [Fine-tune SmolVLA for an SO-101 pick-and-place task on an NVIDIA DGX Spark](https://learn.arm.com/learning-paths/laptops-and-desktops/finetune-smolvla-lerobot/)
- [Run MNIST on an Alif E8 Ensemble DevKit using ExecuTorch and Ethos-U85](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/observing-ethos-u-on-alif/)
- [Train and evaluate Neural Frame Rate Upscaling models using Model Gym](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/model-training-gym-nfru/)
- [Quantize neural upscaling models with ExecuTorch](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/quantize-neural-upscaling-models/)
- [Profile the Performance of AI and ML Mobile Applications on Arm](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/profiling-ml-on-arm/)
- [Enable neural graphics using ML Extensions for Vulkan](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/vulkan-ml-sample/)
- [Build a Sentiment-Aware Voice Assistant with On-Device LLMs](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/voice-sentiment-analysis-with-llm/)
- [Run Vision LLM inference on Android with KleidiAI and MNN](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/vision-llm-inference-on-android-with-kleidiai-and-mnn/)
- [Prepare models for neural graphics with Arm neural technology](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/)
- [Run ExecuTorch Llama 3.2 1B Instruct on an Android phone with Vulkan](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/executorch-vulkan-learning-path/)
- [Profile ONNX model performance with SME2 using KleidiAI and ONNX Runtime](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/performance_onnxruntime_kleidiai_sme2/)
- [Measure LLM inference performance with KleidiAI and SME2 on Android](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/performance_llama_cpp_sme2/)
- [Run LLM inference on Android with KleidiAI, MediaPipe, and XNNPACK](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/kleidiai-on-android-with-mediapipe-and-xnnpack/)
- [Benchmark a KleidiAI micro-kernel in ExecuTorch](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/measure-kleidiai-kernel-performance-on-executorch/)
- [Accelerate LiteRT Models on Android with KleidiAI and SME2](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/litert-sme/)
- [Deploy optimized ML models with ONNX Runtime on Arm platforms](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/onnx/)
- [Enable Neural Super Sampling in Unreal Engine with ML Extensions](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nss-unreal/)
- [Advance robotics reinforcement learning with Isaac Lab on DGX Spark](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_isaac_robotics2/)
- [Build Robot Simulation and Reinforcement Learning Workflows with Isaac Sim and Isaac Lab on DGX Spark](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_isaac_robotics/)
- [Fine-tune neural graphics models using Model Gym](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/model-training-gym/)
- [Enable Neural Frame Rate Upscaling in Unreal Engine](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nfru-unreal/)
- [Analyze Neural Frame Rate Upscaling using Project Moku](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/nfru-cases-study/)
- [Run Llama 3 on a Raspberry Pi 5 using ExecuTorch](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/rpi-llama3/)
- [Visualize Ethos-U NPU performance with ExecuTorch on Arm FVPs](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/)
- [Run a computer vision model on a Himax microcontroller](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/yolo-on-himax/)
- [Edge AI on Arm: PyTorch and ExecuTorch rock-paper-scissors](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/training-inference-pytorch/)
- [Build and run a letter recognition NN model on an STM32L4 Discovery board](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/tflow_nn_stcube/)
- [Build and run the Arm Machine Learning Evaluation Kit examples](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/mlek/)
- [Build and run an image classification NN model on an STM32L4 Discovery board](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/img_nn_stcube/)
- [Build a Privacy-First LLM Smart Home on Raspberry Pi 5](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/raspberry-pi-smart-home/)
- [Use Linux on the NXP FRDM i.MX 93 board](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/linux-nxp-board/)
- [Run a local LLM chatbot on a Raspberry Pi 5](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/llama-python-cpu/)
- [Learn how to run AI on Edge devices using Arduino Nano RP2040](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/edge/)
- [Introduction to TinyML on Arm using PyTorch and ExecuTorch](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/introduction-to-tinyml-on-arm/)
- [Get started with object detection using a Jetson Orin Nano](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/jetson_object_detection/)
- [Deploy ExecuTorch firmware on NXP FRDM i.MX 93 for Ethos-U65 acceleration](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/observing-ethos-u-on-nxp/)
- [Create a ChatGPT voice bot on a Raspberry Pi](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/raspberry_pi_chatgpt_bot/)
- [Port Code to Arm Scalable Vector Extension (SVE)](https://learn.arm.com/learning-paths/servers-and-cloud-computing/sve/)
- [Optimize C++ performance with Profile-Guided Optimization and Google Benchmark](https://learn.arm.com/learning-paths/servers-and-cloud-computing/cpp-profile-guided-optimisation/)
- [Run Phi-3 on Windows on Arm using ONNX Runtime](https://learn.arm.com/learning-paths/laptops-and-desktops/win_on_arm_build_onnxruntime/)
- [Extend OpenClaw for a local-first AI assistant across Arm platforms](https://learn.arm.com/learning-paths/laptops-and-desktops/openclaw_continuum/)
- [Build a Hands-Free Selfie Android Application with MediaPipe](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-android-selfie-app-using-mediapipe-multimodality/)
- [Detect faces with OpenCV on Android Devices](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/android_opencv_facedetection/)
- [Build an Android chat application with ONNX Runtime API](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-android-chat-app-using-onnxruntime/)
- [Build a customer support chatbot on Android with Llama and ExecuTorch](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/)
- [Add an LLM to your Android app with Arm's AI Chat library](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/android-ai-chat-lib/)
- [Build an Android chat app with Llama, KleidiAI, ExecuTorch, and XNNPACK](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/)
- [Build an on-device AI fitness tutor app on Android](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/ai-plank-tutor/)
- [Deploy an MCP Server on Raspberry Pi 5 for AI agent interaction using OpenAI SDK](https://learn.arm.com/learning-paths/cross-platform/mcp-ai-agent/)
- [Profile ExecuTorch models with SME2 on Arm](https://learn.arm.com/learning-paths/cross-platform/sme-executorch-profiling/)
- [Create and train a PyTorch model for digit classification using the MNIST dataset](https://learn.arm.com/learning-paths/cross-platform/pytorch-digit-classification-arch-training/)
- [Build a multimodal retail restocking assistant on Armv9 with MNN](https://learn.arm.com/learning-paths/cross-platform/multimodel_mnn_v9/)
- [Run and benchmark BitNet-2B inference on Arm CPUs with Litespark-Inference](https://learn.arm.com/learning-paths/cross-platform/litespark-inference/)
- [Use Keras Core with TensorFlow, PyTorch, and JAX backends](https://learn.arm.com/learning-paths/servers-and-cloud-computing/keras-core/)
- [Train and deploy XGBoost models on Google Cloud C4A Axion VM](https://learn.arm.com/learning-paths/servers-and-cloud-computing/xgboost-on-axion/)
- [Train and benchmark AI workloads with DeepSpeed on Google Cloud C4A Axion VMs](https://learn.arm.com/learning-paths/servers-and-cloud-computing/deepspeed-on-axion/)
- [Scale AI workloads with Ray on Google Cloud C4A Axion VM](https://learn.arm.com/learning-paths/servers-and-cloud-computing/ray-on-axion/)
- [Run Text Classification with ThirdAI on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/thirdai-sentiment-analysis/)
- [Run distributed inference with llama.cpp on Arm-based AWS Graviton4 instances](https://learn.arm.com/learning-paths/servers-and-cloud-computing/distributed-inference-with-llama-cpp/)
- [Run an LLM chatbot with rtp-llm on Arm-based servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/rtp-llm/)
- [Run a Natural Language Processing (NLP) model from Hugging Face on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/nlp-hugging-face/)
- [Run a Large Language Model (LLM) chatbot with PyTorch using KleidiAI on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/pytorch-llama/)
- [Measure Machine Learning Inference Performance on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/ml-perf/)
- [Measure and accelerate PyTorch Inference on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/torchbench/)
- [Manage the ML lifecycle with MLflow on Google Cloud C4A Axion VM](https://learn.arm.com/learning-paths/servers-and-cloud-computing/mlflow-axion/)
- [Deploy TensorFlow on Google Cloud C4A (Arm-based Axion VMs)](https://learn.arm.com/learning-paths/servers-and-cloud-computing/tensorflow-gcp/)
- [Deploy SqueezeNet 1.0 INT8 model with ONNX Runtime on Azure Cobalt 100](https://learn.arm.com/learning-paths/servers-and-cloud-computing/onnx-on-azure/)
- [Deploy Phi-4-mini model with ONNX Runtime on Azure Cobalt 100](https://learn.arm.com/learning-paths/servers-and-cloud-computing/onnx/)
- [Deploy ModelScope FunASR Model on Arm Servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/funasr/)
- [Deploy DeepSeek-R1 on Arm Servers with llama.cpp](https://learn.arm.com/learning-paths/servers-and-cloud-computing/deepseek-cpu/)
- [Deploy Arcee AFM-4.5B on Arm-based Google Cloud Axion with Llama.cpp](https://learn.arm.com/learning-paths/servers-and-cloud-computing/arcee-foundation-model-on-gcp/)
- [Deploy Arcee AFM-4.5B on Arm-based AWS Graviton4 with Llama.cpp](https://learn.arm.com/learning-paths/servers-and-cloud-computing/arcee-foundation-model-on-aws/)
- [Deploy an AI Agent on Arm with llama.cpp and llama-cpp-agent using KleidiAI](https://learn.arm.com/learning-paths/servers-and-cloud-computing/ai-agent-on-cpu/)
- [Deploy a RAG-based Chatbot with llama-cpp-python using KleidiAI on Google Axion processors](https://learn.arm.com/learning-paths/servers-and-cloud-computing/rag/)
- [Deploy a LLM-based Vision Chatbot with PyTorch and Hugging Face Transformers on Google Axion processors](https://learn.arm.com/learning-paths/servers-and-cloud-computing/llama-vision/)
- [Deploy a Large Language Model (LLM) chatbot with llama.cpp using KleidiAI on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/llama-cpu/)
- [Build RAG applications with LlamaIndex on a Google Cloud C4A virtual machine](https://learn.arm.com/learning-paths/servers-and-cloud-computing/llamaindex-rag-axion/)
- [Build ML Workflow Pipelines with Flyte and gRPC on Google Cloud C4A Axion processors](https://learn.arm.com/learning-paths/servers-and-cloud-computing/flyte-with-grpc/)
- [Build computer vision pipelines with OpenCV on a Google Cloud C4A Axion VM](https://learn.arm.com/learning-paths/servers-and-cloud-computing/opencv-on-axion/)
- [Build and run vLLM on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/vllm/)
- [Build a RAG application using Zilliz Cloud on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/milvus-rag/)
- [Accelerate Whisper on Arm with Hugging Face Transformers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/whisper/)
- [Accelerate Natural Language Processing (NLP) models from Hugging Face on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/benchmark-nlp/)
- [Unlock quantized LLM performance on Arm-based NVIDIA DGX Spark](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/)
- [Orchestrate a persistent local AI agent with Hermes on NVIDIA DGX Spark](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_persistent_agent/)
- [Build a RAG pipeline on Arm-based NVIDIA DGX Spark](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_rag/)
- [Inspect model artifacts and runtime profiles with Google Model Explorer and Arm extensions](https://learn.arm.com/learning-paths/cross-platform/explore-model-artifacts-with-model-explorer/)
- [Run a local AI agent with Ollama to visualize CPU orchestration on Arm](https://learn.arm.com/learning-paths/cross-platform/ai-agent-cpu-orchestration/)
- [Run image classification on an Alif Ensemble E8 DevKit using ExecuTorch and Ethos-U85](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/)
- [Run ERNIE-4.5 Mixture of Experts model on Armv9 with llama.cpp](https://learn.arm.com/learning-paths/cross-platform/ernie_moe_v9/)
- [Build an edge AI Reachy Mini app with Raspberry Pi, MediaPipe, and MuJoCo](https://learn.arm.com/learning-paths/cross-platform/build-a-reachy-robot-app-on-pi/)
- [Run vLLM inference with quantized models and benchmark on Arm servers](https://learn.arm.com/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/)
- [Profile llama.cpp performance with Arm Streamline and KleidiAI LLM kernels](https://learn.arm.com/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/)