top of page
Resources and Industry Insights
This resource and insight hub provides education, breaking news, our research, and more to benefit developers, corporate leadership, academics, marketing and business development professionals, and even those who are new to the concept of AI.
Run OpenAI GPT OSS on NVIDIA Jetson AGX Thor: 120B vs 20B
Running large language models at the edge is becoming practical as embedded platforms continue to scale in performance. In this post, we show how to run OpenAi's GPT-OSS-20B and GPT-OSS-120B models on the NVIDIA Jetson Thor, focusing on real, reproducible inference! Since these are open-weight models, they can be freely tested on different hardware, which makes it interesting to see how they behave beyond data-center systems. We already tried out the GPT-OSS-120B model on a N
David Monge
Feb 195 min read
Running RF-DETR with DeepStream on NVIDIA Jetson Thor
Running RF-DETR with DeepStream is a straightforward way to bring a modern, open-source detector into ready-to-use video analytics pipelines from DeepStream. In this post, we will show what RF-DETR is, how the DeepStream RF-DETR wrapper plugs into nvinfer, and the performance we measured on NVIDIA Jetson Thor, alongside a comparison point for the NVIDIA Jetson Orin AGX.
ridgerun
Feb 184 min read
How to Run OpenAI's GPT OSS 120b on NVIDIA DGX Spark
Learn to run the OpenAI's open source GPT OSS 120b in the NVIDIA DGX Spark computer with our step-by-step guide.
Michael Gruner
Nov 7, 20256 min read
How To Deploy PyTorch Models on Raspberry Pi AI Camera
Learn how to deploy PyTorch models on Raspberry Pi AI Camera with step-by-step optimization, compilation, and packaging for real-time AI inference.
Daniela Brenes
Oct 24, 20255 min read
Getting Started with the Raspberry Pi AI Camera - Sony IMX500
Learn how to set up and use the Raspberry Pi AI Camera with real-time object detection, step by step.
Daniela Brenes
Sep 17, 20254 min read
How to Run a GStreamer Inference Pipeline on Axelera
Deploy a GStreamer inference pipeline on Axelera AI hardware using the Voyager SDK. Learn how to build, run, and extract AI results step-by-step.
Daniela Brenes
Sep 10, 20255 min read
NVIDIA Jetson Thor FAQs Everyone Must Know
NVIDIA Jetson Thor redefines edge AI with up to 2070 FP4 TFLOPS from its Blackwell GPU, 7.5x the AI compute of Jetson Orin, and support for advanced LLM, VLM, and robotics workloads. From humanoid robots to surgical systems and autonomous vehicles, Thor delivers unprecedented performance, efficiency, and scalability for next-gen embedded AI applications.
Marco Madrigal
Aug 11, 20253 min read
Hailo 8 Raspberry Pi Setup Guide for Real-Time AI Inference
Learn how to set up the Hailo-8 AI accelerator on a Raspberry Pi 5 and run real-time inference with minimal setup. This step-by-step guide covers hardware connection, software installation, and executing sample AI pipelines, perfect for anyone starting with edge AI.
Adrian Araya
Jul 29, 20255 min read
Convert ONNX Models to Hailo8L: Step-by-Step Guide Using Hailo SDK
Want to deploy your ONNX model on the Hailo-8L AI accelerator? This step-by-step guide walks you through converting ONNX models to Hailo8L format using the Hailo SDK. Learn how to parse, calibrate, quantize, and compile your models into HEF files ready for real-time inference on edge devices like the Raspberry Pi. Perfect for developers working in embedded AI.
Adrian Araya
Jul 29, 20258 min read
Introducing audio2blendshapes: Turn Voice into Motion
Meet audio2blendshapes, a deep learning model by RidgeRun.ai that converts raw audio into a sequence of blendshape values — the foundational data for facial animation.
Daniela Brenes
Jul 23, 20252 min read
bottom of page