Ivan Fioravanti

📊 LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual benchmark modes (API/CLI), automatic hardware detection (optimized for Apple Silicon), visual performance charts.

Examples on how to use various LLM providers with a Wine Classification problem

Qwen Image models through MPS

Z Image models through MPS

Chatbot Ollama is an open source chat UI for Ollama.

Bootstrap Kubernetes the hard way on Microsoft Azure Platform. No scripts.

Ollama's Interactive Prompt Engineering Tutorial

A command-line utility to manage MLX models between your Hugging Face cache and LM Studio.

Grammar checker with a keyboard shortcut for Ollama and Apple MLX with Automator on macOS.

The ultimate training toolkit for finetuning diffusion models

Apple MLX port of FasterLivePortrait for Apple Silicon

Animate portrait photos and videos on Apple Silicon Macs using AI, feed it a webcam, video, audio, or text to make still images move and speak. No GPU required, runs on Mac's unified memory via Apple's MLX framework.

Turn the Hacker News front page into local AI art. Powered by mlx-vlm, MFlux, and Apple Silicon.

Perf monitoring CLI tool for Apple Silicon

Provider-agnostic, open-source evaluation infrastructure for language models

No description.

OpenSource deployment made easy

No description.

DeepSeek 4 Flash local inference engine for Metal

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

Bringing the Unsloth experience to Mac users via Apple's MLX framework

Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

CanalSplat - An interactive gallery showcasing Canaletto's Venice paintings as 3D Gaussian Splats. Explore iconic Venetian views in an immersive web experience, featuring a curated selection of Canaletto masterpieces rendered as interactive 3D scenes.

A place to store benchmarks results on Apple Silicon Mx machines running MLX, llama.cpp, LM Studio, Ollama or anything else relevant for the community.

Run LLMs with MLX

No description.

MCP server for interacting with RabbitMQ

Community maintained hardware plugin for vLLM on Apple Silicon

OpenSource Claude Cowork. A desktop AI assistant that helps you with programming, file management, and any task you can describe.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

A simple UI / Web / Frontend for MLX mlx-lm using Streamlit.

Very simple benchmarks around Apple mlx

A collection of guides and examples for the Gemma open models from Google.

A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon.

Fast, flexible LLM inference

The open-source AI chat app for everyone.

No description.

Anthropic's Interactive Prompt Engineering Tutorial

Optimized Ollama LLM server configuration for Mac Studio and other Apple Silicon Macs. Headless setup with automatic startup, resource optimization, and remote management via SSH.

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

Post-training with Tinker

A CLI to estimate inference memory requirements for Hugging Face models, written in Python.

No description.

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

ollama like cli tool for MLX models on huggingface (pull, rm, list, show, serve etc.)

Modeling, training, eval, and inference code for OLMo

No description.

Chat with your data natively on Apple Silicon using MLX Framework.

No description.

No description.

No description.

mactop - Apple Silicon Monitor Top

Community model zoo + knowledge base for Apple Core AI (iOS/macOS 27): Qwen3.5 & Gemma 4 converted end-to-end, verified on-device (iPhone 17 Pro GPU/ANE), conversion gotchas, custom Metal kernels, Swift runner

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Archived educational snapshot of the Repo Prompt app

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

An experiment, what if Gemma had a Desktop app tuned for the model and offline scenarios?

Measuring frontier coding agents on original, long-horizon engineering tasks

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Benchmark harness for Ratel: BM25 retrieval evaluation + agent-campaign with LLM judge

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Lossless DFlash speculative decoding for MLX on Apple Silicon

No description.

No description.

The agent that grows with you

llama-benchy - llama-bench style benchmarking tool for all backends

Comparison between open source PI agent and closed source Claude Code agent

REAP expert pruning for MoE LLMs on Apple Silicon via MLX

'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and other APIs running on your Mac through a single aggregated OpenAI-compatible API endpoint. Supports Apple Vision and single command (non-server) inference with piping as well . Now with Web Browser and local AI API aggregator

An OS for your agents, built for your pocket.

Automated hyperparameter search for optimal Gabliteration configurations on large language models

this repo has all official MLX-LM-LoRA example notebooks for training on Apple Silicon

mlx-lm server wrapper for agentic harness

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

No description.

Train Large Language Models on MLX.

No description.

Find the hidden meaning of LLMs

Examples using MLX Swift

🐚 OpenDevin: Code Less, Make More

Gets your TFLOPs for your GPU quickly

LM Studio Apple MLX engine

Fast parallel LLM inference for MLX

Lightweight framework for building Agents with memory, knowledge, tools and reasoning.

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

TFLOPs testing on MPS and CUDA

FastMLX is a high performance production ready API to host MLX models.

Hierarchical Reasoning Model Official Release

No description.

MLX-GUI MLX Inference Server

MLX: An array framework for Apple silicon

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

No description.

Human Eval scores evaluated locally using a 3090

Examples in the MLX framework

Core-to-core latency benchmark that works on MacOS without hard affinity

No description.

Run large models from the terminal using Apple MLX.

Support for MLX models in LLM

Access large language models from the command-line

No description.

MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seamless integration with existing OpenAI SDK clients while leveraging the power of local ML inference.

No description.

MLX-based QA pair generator and LLM finetuning tool in Streamlit

This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open sourced AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.

🥨 Lobe Icons - Popular AI / LLM Model Brand SVG Logo and Icon Collection.

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

Implementation of F5-TTS in MLX

Interrogate LLMs to solve corporate mysteries.

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

aider is AI pair programming in your terminal

No description.

Benchmarks comparing PyTorch and MLX on Apple Silicon GPUs

A MLX port of FLUX based on the Huggingface Diffusers implementation.

Utilities to use the Hugging Face Hub API

ChatMLX is a large model real-time conversation app implemented using MLX.🚧

No description.

Very basic framework for parameterized large language model (Q)LoRa fine-tuning using mlx, mlx_lm, and OgbujiPT. Architecture for systematic running of easily parameterized fine-tunes

A reinforcement learning framework based on MLX.

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

No description.

No description.

Benchmark of Apple's MLX operations on mlx gpu, cpu, torch mps and cuda.

No description.

Enhanced ChatGPT Clone: Features OpenAI, Assistants API, Azure, Groq, GPT-4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development

Code snapshots and materials for our "React - The Complete Guide" course (https://acad.link/reactjs)

mlx image models for Apple Silicon machines

This is our own implementation of 'Layer Selective Rank Reduction'

No description.

ChatGPT-Style Web UI Client for Ollama 🦙

Create your own AI by fine-tuning open source models

Scripts to create your own moe models using mlx

Integrate cutting-edge LLM technology quickly and easily into your apps

From anywhere you can type, query and stream the output of an LLM or any other script

No description.

Code that accompanies the book "Linear Algebra for Data Science"

Get up and running with Llama 2 and other large language models locally

Hackable and optimized Transformers building blocks, supporting a composable construction.

Experiments with local as well as models available through an api

First token cutoff sampling inference example

GGUF implementation in C as a library and a tools CLI program

Port of Andrej Karpathy's nanoGPT to Apple MLX framework.

No description.

The MongoDB Database

⏩ the open-source autopilot for software development—bring the power of ChatGPT to VS Code and JetBrains

Advanced Python Mastery (course by @dabeaz)

⚡ Building applications with LLMs through composability ⚡

Distributed Application Framework for .NET

This repo includes ChatGPT prompt curation to use ChatGPT better.

Lightweight workflow engine for .NET Standard

How to set up the Elastic stack on Kubernetes

Thoughtfully architected, obscenely fast, thoroughly enjoyable web services for all