README.md

metadata

title: README
emoji: 🦀
colorFrom: indigo
colorTo: purple
sdk: static
pinned: false

Explore Arm-Optimized Learning Paths on Hugging Face

Arm’s AI development resources help you deploy faster with optimized performance on Arm by default. The resources highlight Arm integrations with major OSes and frameworks to simplify development and enable scalability and portability for your applications.

Follow our curated Learning Paths to explore Arm-optimized AI models available in our Hugging Face Model Collections, and to streamline your journey from discovery to deployment on Arm.

Learning Path	Market Application	Model(s) Featured
Generative AI
Build a RAG application using Zilliz Cloud on Arm servers	Cloud & Datacenter	All Minilm L6 V2
Accelerate NLP models from Hugging Face on Arm servers	Cloud & Datacenter	Distilbert Base Uncased Finetuned Sst 2 English
Deploy a Large Language Model (LLM) chatbot with llama.cpp using KleidiAI on Arm servers	Cloud & Datacenter	Dolphin 2.9.4 Llama3.1 8B Gguf
Build a RAG application using Zilliz Cloud on Arm servers	Cloud & Datacenter	Dolphin 2.9.4 Llama3.1 8B Gguf
Run a Large Language Model (LLM) chatbot with PyTorch using KleidiAI on Arm servers	Cloud & Datacenter	Llama 3.1 8B Instruct
Deploy a RAG-based Chatbot with llama-cpp-python using KleidiAI on Google Axion processors	Cloud & Datacenter	Llama3.1 8B Gguf
Build an Android chat app with Llama, KleidiAI, ExecuTorch, and XNNPACK	Smartphone	Llama 3.2 1B Instruct
Run a local LLM chatbot on a Raspberry Pi 5	Raspberry Pi	Orca Mini 3B Gguf
Build an Android chat application with ONNX Runtime API	Smartphone	Phi 3 Vision 128K Instruct Onnx Cuda
Run an LLM chatbot with rtp-llm on Arm-based servers	Cloud & Datacenter	Qwen2 0.5B Instruct
Build and Run a Virtual Large Language Model (vLLM) on Arm Servers	Cloud & Datacenter	Qwen2.5 0.5B Instruct
LLM inference on Android with KleidiAI, MediaPipe, and XNNPACK	Smartphone	Gemma 2B
Run Llama 3 on a Raspberry Pi 5 using ExecuTorch	Raspberry Pi	Llama 3.1 8B
CV: Image Classification & Object Detection
Profile the Performance of AI and ML Mobile Applications on Arm	Smartphone	Mobilenet V2 1.0 224
Run a Computer Vision Model on a Himax Microcontroller	IoT	Yolov8
Sentiment Analysis
Run a Natural Language Processing (NLP) model from Hugging Face on Arm servers	Cloud & Datacenter	Twitter Roberta Base Sentiment Latest
Accelerate NLP models from Hugging Face on Arm servers	Cloud & Datacenter	Distilbert Base Uncased Finetuned Sst 2 English

Arm Kleidi: Unleashing Mass-Market AI Performance on Arm

Arm Kleidi developer enablement technologies and kernel libraries unlock AI performance across the world's popular AI frameworks and runtimes, accelerating AI workloads everywhere on Arm. Ecosystem integrations help application developers achieve top performance by default and future-proof performance, with no additional work or skills investment.

Useful Resources on Arm Kleidi:

• Arm KleidiAI for optimizing any AI framework: Gitlab repo and blog
• Arm KleidiCV for optimizing any computer vision framework: Gitlab repo and blog
• Arm Compute Library for all AI software

Note: The data collated here is sourced from Arm and third parties. While Arm uses reasonable efforts to keep this information accurate, Arm does not warrant (express or implied) or provide any guarantee of data correctness due to the ever-evolving AI and software landscape. Any links to third-party sites and resources are provided for ease and convenience. Your use of such third-party sites and resources is subject to the third party’s terms of use, and use is at your own risk.