THE LATEST<\/p>\n<\/div>
Recent Intelligence<\/div><\/h2><\/div>Continuous updates from the frontiers of embedded artificial intelligence and performance engineering.<\/p>\n<\/div><\/div><\/div>
Explore All Posts \u00bb<\/a><\/p>\n<\/div><\/div><\/div><\/div>\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/12\/dgx-spark-cluster.webp\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>AI Cluster<\/a>, Generative AI<\/a><\/span><\/span><\/div><\/div><\/div><\/div>Building a High-Speed AI Cluster with 4 DGX Spark Systems<\/a><\/h1><\/div> For large AI models, the limiting factor is often not just compute performance, but memory capacity... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/12\/33.jpg\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>Generative AI<\/a>, Performance<\/a><\/span><\/span><\/div><\/div><\/div><\/div>NVIDIA DGX Spark vs NVIDIA Jetson Thor<\/a><\/h1><\/div> One of the most common mistakes made when developing artificial intelligence systems is evaluating ... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/10\/32.jpg\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>Getting Started<\/a><\/span><\/span><\/div><\/div><\/div><\/div>NVIDIA DGX Spark: Bringing Data Center Power to Your Desk<\/a><\/h1><\/div> Artificial intelligence is entering a new era\u2014one where supercomputing performance is no longer con... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/09\/a.jpg\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>Generative AI<\/a><\/span><\/span><\/div><\/div><\/div><\/div>HammerBench : AGX Thor\u2019s Power Meets Ollama<\/a><\/h1><\/div>What is an LLM benchmark and why is it important? LLM benchmarks are standardized tests designed to... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/09\/b.jpg\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>Generative AI<\/a><\/span><\/span><\/div><\/div><\/div><\/div>How to Run Llama.cpp Server on Jetson AGX Thor?<\/a><\/h1><\/div>Llama.cpp Server on Jetson AGX Thor: Unlocking Edge AI with Large Language Models Llama.cpp Server ... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/09\/d.jpg\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>Generative AI<\/a><\/span><\/span><\/div><\/div><\/div><\/div>How to Run MLC LLM on Jetson AGX Thor?<\/a><\/h1><\/div>What is MLC LLM ? MLC LLM (Machine Learning Compilation for Large Language Models) is an open-source... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n<\/div><\/i><\/div><\/i><\/div><\/div><\/div><\/div><\/div><\/div>Getting Started<\/h2><\/h3><\/div><\/div><\/div>All Guides<\/a><\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div>- \n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div><\/div><\/div>Categories: Getting Started<\/a><\/span><\/span><\/div>
NVIDIA DGX Spark: Bringing Data Center Power to Your Desk<\/a><\/h2><\/div> Artificial intelligence is entering a new era\u2014one wher... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div><\/div><\/div><\/li>\n- \n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t
![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/08\/31.jpg\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div><\/div><\/div>Categories: Getting Started<\/a><\/span><\/span><\/div>NVIDIA JetPack 7.0: Powering the Next Generation of AI and Robotics at the Edge<\/a><\/h2><\/div> NVIDIA has announced the release of JetPack\u2122 7.0, the ... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div><\/div><\/div><\/li>\n- \n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t
![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/08\/30.jpg\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div><\/div><\/div>
Continuous updates from the frontiers of embedded artificial intelligence and performance engineering.<\/p>\n<\/div><\/div><\/div>
Explore All Posts \u00bb<\/a><\/p>\n<\/div><\/div><\/div><\/div> For large AI models, the limiting factor is often not just compute performance, but memory capacity... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n One of the most common mistakes made when developing artificial intelligence systems is evaluating ... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n Artificial intelligence is entering a new era\u2014one where supercomputing performance is no longer con... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n What is an LLM benchmark and why is it important? LLM benchmarks are standardized tests designed to... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n Llama.cpp Server on Jetson AGX Thor: Unlocking Edge AI with Large Language Models Llama.cpp Server ... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n What is MLC LLM ? MLC LLM (Machine Learning Compilation for Large Language Models) is an open-source... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div>\n<\/div> All Guides<\/a><\/p>\n<\/div><\/div><\/div><\/div> Artificial intelligence is entering a new era\u2014one wher... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div><\/div><\/div><\/li>\n NVIDIA has announced the release of JetPack\u2122 7.0, the ... Continue Reading\u2192<\/a><\/p><\/div><\/div><\/div><\/div><\/div><\/li>\n\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>Building a High-Speed AI Cluster with 4 DGX Spark Systems<\/a><\/h1><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>NVIDIA DGX Spark vs NVIDIA Jetson Thor<\/a><\/h1><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>NVIDIA DGX Spark: Bringing Data Center Power to Your Desk<\/a><\/h1><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>HammerBench : AGX Thor\u2019s Power Meets Ollama<\/a><\/h1><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>How to Run Llama.cpp Server on Jetson AGX Thor?<\/a><\/h1><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div>How to Run MLC LLM on Jetson AGX Thor?<\/a><\/h1><\/div>
Getting Started<\/h2><\/h3><\/div><\/div><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div><\/div><\/div>NVIDIA DGX Spark: Bringing Data Center Power to Your Desk<\/a><\/h2><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div><\/div><\/div>NVIDIA JetPack 7.0: Powering the Next Generation of AI and Robotics at the Edge<\/a><\/h2><\/div>
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div><\/div><\/div>
![\"\"](\"https:\/\/blog.openzeka.com\/en\/wp-content\/uploads\/2025\/07\/PULSAR-D315-5G_Flashing_Guide.webp\")
\t\t\t<\/a>\n\t\t\t\t\t\t\t<\/div>\n<\/div><\/div><\/div>