https://sudonull.com/running-moe-gpt-oss-120b-on-6-gb-gpu-up-to-30-t-s
Accelerating GPT-OSS-120B on a weak GPU with -cmoe and --fit. Efficient RAM usage for MoE models. Instructions for developers.
Search Articles — Sudonull
Search Results
In this project
https://sudonull.com/local-ai-on-rtx-3090-mining-build
Build on H510 Pro BTC+ and 3 RTX 3090 for gpt-oss-120b: 110 t/s inference, loading optimization. Tests, diagrams, costs for LLM developers.
https://sudonull.com/vite-8-0-with-rust-bundler-rolldown-key-changes
Vite 8.0 switches to a single Rust bundler Rolldown, speeding up builds by 10–30×. Full OSS stack with Void for full-stack. Learn about SSR benchmarks and memory leaks. For middle/senior dev.
Trending Now
How to Become a Self-Taught Programmer and Get a Job
Learn how to become a self-taught programmer and get a job in 2026 with this practical roadmap. Master fundamentals, build a portfolio, and land your first developer role.
Figure 02: new humanoid robot with AI interface from Figure AI
Figure AI introduced the humanoid robot Figure 02 with physical AI and OpenAI language model. The robot passed tests at BMW factories. Learn how humanoid robots are changing manufacturing.
Docker Container Networking Explained: A Practical Guide
Docker container networking explained in depth: learn bridge vs host networks, DNS, port publishing, and how to build secure, scalable multi-container apps.
What Is Infrastructure as Code? Benefits, Tools & Best Practices
Learn what is infrastructure as code and why use it. Discover key benefits, essential tools, and best practices to automate and secure your cloud infrastructure.
Top 10 Breakthrough Technologies 2026 from WEF: Full Analysis
Analysis of trends, hidden risks, and geopolitical implications of Top 10 Emerging Technologies 2026. Who benefits from new developments and who loses. Read the analytics.
What Is a Vector Database? Beginner's Guide to AI Search
What is a vector database? Learn how vector databases power AI search, RAG, and recommendations. Discover key concepts and when to use them. Start here.
How Does Retrieval Augmented Generation Work? RAG Guide
Learn how does retrieval augmented generation work: RAG reduces AI hallucinations, grounds responses in real data, and transforms LLMs into trustworthy systems. Start now.
Fine Tuning vs Retrieval Augmented Generation: A Guide
Compare fine tuning vs retrieval augmented generation for LLMs. Learn which approach suits your AI project based on accuracy, cost, and data freshness.
Semiconductor Industry History & How It Works
Explore the history of the semiconductor industry and how does it work. Learn chip design, fabrication, and the global impact of this vital technology. Discover more.
How to Set Up CI/CD Pipeline with GitHub Actions – Guide
Learn how to set up CI/CD pipeline with GitHub Actions. Step-by-step guide with YAML examples for automated testing, Docker builds, and deployment.