Fabio Matricardi

GPT4All_Medium. Repo of the code from the Medium article

cdQnA. repository for documents and studies about closed domain question and answering with LLM

Deepseek-R1-qwen1.5B. how to run DeepSeek-R1-Distill-Qwen-1.5B GGUF locally on your PC

LaMiniPower. The power of a small LLM for your domain knowledge QnA

How-I-Built-a-Chatbot-that-Crushed-ChatGPT. Repo of the code from the Medium article

ModernFastAPI. Repo of the code from the Medium article - Build a powerful LLM API right on your computer

ChatBOTMastery. Your Chatbot Mastery: build a super small custom AI assistant with Gradio_client Python and Streamlit - Chapter 1

TiniLlamaGradioChat. Repo for a ChatBot, with Gradio, Streaming TinyLlama1.1BOpenOrca.gguf on CPU only

AI-ExtractData-NuExtract-tiny. NuExtract-tiny GGUF for data extraction in json format

My-2B-Reflection-LLM. How to build your own Reflection LLM with only 2B parameters model

YouAreTheBenchmark. Personal Catalog of prompt templates for NLP tasks

whisperCPP-streamlit. Repo of the code from the Medium article

LaminiChat. Repo of the code from the Medium article Say Goodbye to OpenAI part2

HFChatbot. Repo of the code from the Medium article: Say Goodbye to OpenAI

YourFastAPI. Repo of the code from the Medium article A FastAPI for your Local LLM

openvino-api-server. my personal attempt to openai API compatible openvino server

Gemma2B-ChatAssistant. Maybe Gemma-2B-IT is the smallest and best chat friend you can have

NanollavaCPP. nanollava with virtualenv python3.11 llamacpp-python and streamlit

danube3-0.5b-chat. stramlit AI assistant with llamacpp and H2O danube3

RuleThemAll. Repo of the code from the Medium article

Gemma2-2b-it-chatbot. Repo of the code from the Medium article about running Gemma2 2b locally

LlamaFile-4-ALL. A quantized LLM and API webserver in one single executable file

135M-you-cannot-go-Smaller. Repo of the code from the Medium article 135M: you cannot go Smaller

Mistral-DesktopApp. Streamlit Chat-bot with Mistral.ai free API into a standalone Windows Desktop App

GradioLangchainCustomLLM. How to build a Custom LLM wrapping a Gradio API call into Langchain

llmwareSLIMS. Repo of the code from the Medium article

17megabyteCHATBOT. Repo of the code from the Medium article

Gemma2-9b-GradioClient. Run with API call to Hugging Face Spaces Gemma2-9B model

KingOfTheTiny. Repo of the code from the Medium article about TinyVicuna1B GGUF

NuExtract-1.5-openvino. Extract data with LLM and openvino

YourAIPhotoStory. Repo of the code from the Medium article Create your own AI powered Photo story

llamaCPPServerVisual. llama.cpp server running InternVL-2.5-1b locally

twitterStoryCreator. Repository for the Article on Medium about Serverless GPU

llamacppChatDocs. Chat with your documents using only LlamaCPP and Langchain

Qwen3-4bChatDocs. Textual interface to chat with your documents using llama-cpp server and Qwen3-4b.gguf

NuEtract1.5-streamlit. simple use of LLM extracting structured data from plain text

Playgrounds. Repo of the code from the Medium article

llamaCPP_Agents. Run AI agents with llama-cpp-agents locally

OpenVINO-Gemma2B-streamlit. Using OpenVINO with Gemma2-2B INT4 and streamlit CHAT APP

MetadataIsAllYouNeed. Repo of the code from the Medium article Metadata Metamorphosis: from plain Data to Enhanced insights with Retrieval Augmented Generation

ZephyrGPT4ALL. Test of Chat with documents and RAG reranking multi-language with Zephyr7b GPTQ

AI-RewriteText. Medium article repo to use LaMini AI to rewrite text

phi-3-miniTEST. Repo of the code from the Medium article

StableDiffusionCPP-usage. Create images with dreamshaper_8 on your CPU

OpenELM270M-test. Repo of the code from the Medium article

ImageUpscaler. Streamlit App to Upscale images and compared visualization - Repo of the code from the Medium article

thePromptBattle. Repo of the code and results from the Medium article Battle of the Prompts: Unveiling the True Capabilities of Open Source Language Models

Gemini2FlashInChina. Open Router ai Gradio client for Gemini2 flash working also in China

Mistral-LeChat. all you need to start with Le Chat Mistral API

Qwen3-0.6bReason. llamacpp server and qwen3 textual chat interface with reasoning options

llamacpp-speculative. llama-cpp-python server with speculative decoding

LFM2-localAI. Quick chat interface with LFM2-700M and llama.cpp server

OPENVINO-betterStreamer. Textual Interface for Gemma2-2B Openvino with streaming effect

qwen2.5-1.5b-testbench. run GGUF qwen2.5-1.5b with llamaCPP-python

nanoLlava-cpp. How to run nanollava with llama-cpp-python

HowSmalltoChatYouCanGo. Repo of the code from the Medium article

Qwen2.5ChatDocs. A gradio Chatbot with llamaCPP server and Qwen2.5 3B for your documents

BattleOfTheTiny-part1. Repo of the code from the Medium article

smolLM2-GradioChatbot. a Gradio Chatbot with llama-server backhand

OLMOE_llamaCPP. Streamlit chatbot with llama.cpp and OLMoE from AllenAI AI2