InGoPenAIbyJatinkumar Parmar·Aug 1Accelerating Llama3.3–70B with Quark MXFP4 quantization for vLLMAuthor: Charles Yang , jatinkumar parmar Knowledge level: Beginner
Syed Shahriyar Ali·Dec 12, 2025Beyond RAG: Building an Intelligent Shipment Query System with Tool CallingThe Problem That Started It All
Ressa_agustika·Nov 21, 2025Membangun AI Pribadi yang Aman: Instalasi Ollama AI-Models untuk Melindungi Privasi Data Anda1. Pendahuluan
InEngineering@ClouderabyUMESH CHAUDHARY·Oct 15, 2025Serving the Open Source LLMs On Multi-GPU Host SetupThis story outlines the procedures undertaken to configure a multi-GPU host within the datacenter for the purpose of hosting and serving…
Sung-Cheol Kim·Feb 3, 2025Building a Local LLM Server: How to Run Multiple Models EfficientlyI’m writing a series on how to utilize a home Ubuntu server as a local LLM server. While working on LLM projects, I’ve pondered how…
InTowards AIbyMd Monsur ali·Dec 9, 2024Control LLM’s Output with Ollama: Structured Outputs Made EasyLearn how to easily harness Ollama’s powerful APIs to generate structured data, enabling seamless integration and automation for your…
OmarEbnElKhattab Hosney·Nov 28, 2024Analyzing How Different LLMs Handle a Paradoxical QuestionIn a recent funny experiment, I tested four open-source language models using LM Studio on an Ubuntu system equipped with an RTX 4090. The…
InLevel Up CodingbyMd Monsur ali·Nov 11, 2024Build Your Talking Voice AI Assistant Locally: Memory-Retaining Chatbot with Streamlit UI…Step-by-Step Guide to Developing Your Own Voice AI with Context Memory and Real-Time Chat, Powered by Llama3.1 & Llama3.2 ModelsA response icon1A response icon1
InLevel Up CodingbyMd Monsur ali·Oct 21, 2024Building Your Personal AI Assistant with Memory Using Ollama’s Llama3.1,Learn how to create your own AI assistant with chat history recall, multi-model support, and flexible inference settings, powered by…A response icon2A response icon2
InDev GeniusbyTim Urista | Senior Cloud Engineer·Oct 17, 2024Fine-Tuning Llama 3.1 8B with Minimal Data: A Hands-On GuideTeach Llama 3.1 to generate custom outputs using minimal data, Unsloth, and Google Colab.
