Educational content, tutorials and insights on the future of AI infrastructure.

Tutorial

How to run Qwen 3 235B on a cloud GPU

Discover how to deploy Qwen 3 235B model with Ollama and OpenWebUI on a cloud GPU and check out our model analysis.

Tutorial

How to run Llama 4 on a cloud GPU with Transformers and vLLM

Learn how to run Meta’s multimodal Llama 4 models with Hugging Face Transformers and vLLM on an Ori cloud GPU, and check our comparison of Llama 4 vs...

AI

What is Reinforcement Learning (RL)?

Explore reinforcement learning (RL), how it works, and essential RL techniques such as Q-learning, policy gradient, and actor-critic methods.

Product updates

NVIDIA H200 GPUs Now Generally Available on Ori Global Cloud

Accelerate your AI with NVIDIA H200 GPUs on Ori to train models and run inference more efficiently than ever before.

Tutorial

How to run Mistral Small 3 on a cloud GPU with vLLM

Discover how to easily deploy Mistral Small 3 on a cloud GPU with vLLM and our model analysis with verbal, math and coding prompts.

Tutorial

How to run DeepSeek R1 on a cloud GPU with Ollama

Learn how to easily deploy DeepSeek R1 Distill 70B on an H100 GPU with Ollama and OpenWebUI, plus our thoughts about the model and its innovative...

LLM

Deploy and scale Qwen 2.5 with just one click on Ori Inference Endpoints

Learn how to deploy and scale Qwen 2.5 1.5B effortlessly with Ori Inference Endpoints.

Tutorial

How to run Llama 3.3 70B on a cloud GPU

Learn how to deploy Meta’s new text-generation model Llama 3.3 70B with Ollama and Open WebUI on an Ori cloud GPU.

GPU

An overview of the NVIDIA H200 GPU

Inside the NVIDIA H200: Specifications, use cases, performance benchmarks, and a comparison of H200 vs H100 GPUs.

Tutorial

How to run Genmo Mochi 1 video generation on a cloud GPU

Discover how to deploy Genmo Mochi 1 with ComfyUI on an Ori GPU instance, and read our analysis of this new open source video generation model.

GPU

Everything you need to know about the NVIDIA L40S GPU

Learn more about the NVIDIA L40S, a versatile GPU that is designed to power a wide variety of applications, and check out NVIDIA L40S vs NVIDIA H100...

Case study

nCompass (YC W24) leverages Ori Serverless Kubernetes to make AI inference 2x cost-effective

Find out how Ori Serverless Kubernetes is helping nCompass run cost-effective LLM inference at scale.