Artificial Intelligence

NYU Shanghai Library > RITS Home > *

Comprehensive AI Tools & Models Directory

💬

Language Processing

🤖 Language Models

📖 Open Source Models

💡 These models come in different sizes, choose the one that fits your computer specifications.

Open Source

✍️ Creative Writing

Perfect for storytelling, content creation, and creative tasks

Gemma 4 Collection

Open Source

👨‍💻 Coding

Specialized models for code generation and programming assistance

Qwen 3 Coder Collection Qwen3-Coder-Next Devstral Small 1.1 Qwen3.6-27B Qwen3.6-35B-A3B

Open Source

🌐 General Purpose

Versatile models for everyday tasks and general conversations

Qwen 3 Collection Qwen 3.5 Collection Qwen3.5-Omni Mistral Small 4 Muse Spark Mistral Medium 3.5 Granite 4.1 Bonsai 27B

Open Source

🌍 Multilingual

Support for 140+ languages with vision capabilities

Ministral 3 Collection

Open Source

🤖 Agentic

Advanced reasoning and task planning capabilities

Qwen 3.5 Collection Trinity-Large-Thinking NVIDIA Nemotron 3 Super Needle

Open Source

🚀 Huge Models

State-of-the-art performance requiring high-end hardware

DeepSeek V4 Collection Kimi K2.6 GLM-5.2 GLM-4.7-Flash MiniMax M3 Inkling LongCat-2.0 Hy3 MiMo-V2.5-Pro

Open Source

👁️ Vision-Language (VLMs)

Multimodal models that understand images + text

Gemma 4 (Vision) Qwen 3.5 (Native VL) EXAONE 4.5 MiniCPM-V 4.6 Lance

🔒 Closed Source Models

API Only

✍️ Creative Writing

Industry-leading creative capabilities

Claude Opus 4.8 Claude Fable 5

API Only

🌐 General Use

Google’s flagship multimodal AI

Gemini 3.5 Claude Fable 5 Claude Sonnet 5

API Only

👨‍💻 Coding

Best-in-class code generation

Claude Opus 4.8 GPT-5.6 Claude Fable 5

API Only

🌍 Multilingual

Advanced multilingual capabilities

GPT-5.6

API Only

🤖 Agentic

Advanced AI agents and automation

Claude Opus 4.8

🖥️ Model Running Applications

LM Studio – Easiest

User-friendly interface for running LLMs locally

Official Website

Ollama – No UI

Local LLM runner with simple CLI interface

Official Website

Llama.cpp – Dev friendly, no GPU needed

C++ implementation for running LLMs on CPU

GitHub

vLLM – Dev friendly, GPU needed

High-throughput LLM serving engine

GitHub

Lemonade Server

Lightweight, production-ready inference server

Official Website

🎨

Image Generation

Open Source

🖼️ General Purpose

High-quality text-to-image generation

FLUX Collection Qwen-Image Collection ERNIE-Image Krea 2 Ideogram 4.0

Open Source

🖌️ Image Editing

Instruction-following, mask-free image editing

Qwen-Image-Edit FLUX.1-Kontext-dev

API Service

✂️ Inpainting / Editing

Advanced context-aware image editing

FLUX Kontext 🍌Gemini Image Generation

Open Source

⚡ Fast Generation

Ultra-fast, efficient image generation

Sana Collection FLUX Schnell Z-Image / Z-Image-Turbo Collection Bonsai Image 4B

API Only

⚡ Fast Generation

Pro-quality image generation at flash speed, default across Google products

Nano Banana 2 (Gemini 3.1 Flash Image)

API Only

🧠 Reasoning Generation

Image generation with reasoning mode and 2K output

ChatGPT Images 2.0 (gpt-image-2)

🎬

Video Generation

Open Source

🏆 Quality

High-quality video generation, including native 2K with synchronized audio

Wan2.2 GitHub MiniMax H3 (Hailuo 3.0) H3 License (excludes US/EU/UK/KR)

Open Source

⚡ Fast

Lightweight video generation with portrait support and audio

LTX-2.3 FastWan

API Only

🌟 Accessible

Hosted video generation platforms

Wan 2.5 Hailuo 3 (MiniMax)

API Only

🚀 State-of-the-Art

Leading research-grade video models

Veo 3.1 Seedance 2.0

🔊

Audio Processing

Open Source

🗣️ Text-to-Speech

High-quality voice synthesis

Kokoro TTS Dia VoxCPM 1.5 Collection KittenTTS Qwen3-TTS Voxtral TTS

API Service

🎙️ Text-to-Speech

Studio-grade voices and streaming TTS

ElevenLabs Gemini 3.1 Flash TTS

API Service

🎧 Realtime Voice

Full-duplex speech-to-speech conversation

GPT-Live GPT-Realtime-2

Open Source

👂 Speech-to-Text

Accurate transcription and translation

Whisper Collection Voxtral Transcribe 2 Qwen3-ASR Cohere Transcribe

Open Source

🎵 Music Generation

AI music generation from text prompts

ACE-Step 1.5 Foundation-1

👁️

Computer Vision

Open Source

🎯 Object Detection

Real-time object detection and tracking

YOLOv8 YOLOv10 SAM 3 Collection SAM 3D Body Collection

Open Source

🏷️ Image Classification

Advanced image recognition and classification

Vision Transformers ResNet Models

Open Source

📄 Document Understanding

High-accuracy document parsing and OCR

GLM-OCR

🧊

3D Model Generation

API Service

🎲 3D Mesh Generation

Create 3D models from text descriptions

Tripo3D Meshy Shap-E

Open Source

🏃 Motion Generation

Text-to-3D skeletal motion for animation and character control

HY-Motion 1.0 Kimodo

Open Source

🌐 World Generation

Auto-expanding 3D world and multi-modal world models

HY-World 2.0 Marble 1.1

🛠️

AI Development Tools

💻 AI Coding Assistants

Claude Code

Agentic command line coding tool by Anthropic

Official Announcement

GitHub Copilot

AI pair programmer for VS Code and other IDEs

Official Website

Cline

Autonomous AI assistant for VS Code

GitHub

Cursor

AI-first code editor built for pair programming

Official Website

Gemini CLI

Google’s command-line AI agent powered by Gemini models

Documentation

Qwen Code

Command-line AI workflow tool optimized for Qwen3-Coder

GitHub

OpenAI Codex

OpenAI’s latest code generation assistant

Overview

Google Antigravity

Google’s experimental AI coding assistant experience

Official Website

Claude 4.6 (for Coding)

Anthropic’s latest Claude series tuned for strong coding performance

Release Notes

Leanstral

Mistral’s open-source proof agent for Lean 4

Hugging Face

🔧 Fine-tuning Platforms

Unsloth / Unsloth Studio

Fast fine-tuning for LLMs with no-code UI

GitHub

PEFT

Parameter-Efficient Fine-Tuning

Documentation

MS-Swift

Multi-modal fine-tuning framework by ModelScope

GitHub

ml-intern

Open-source agent that automates LLM post-training

GitHub

☁️ Model Deployment

Hugging Face Inference

Managed model hosting

Documentation

Modal

Serverless GPU computing

Official Website

🤖 AI Orchestration

LangChain

Build LLM applications

GitHub

Microsoft AutoGen

Multi-agent conversations

GitHub

📊 Vector Databases

Chroma

Open-source embedding database

GitHub

🧩 Model Context Protocol (MCPs)

Model Context Protocol

Standard for connecting tools to AI assistants

Website

context7

Serverless contexts for MCP (Upstash)

GitHub

Awesome MCP Servers

Curated list of MCP servers

GitHub

🔗 Graph Databases

Neo4j

High-performance graph database for connected data

Official Website

📈 Evaluation Tools

OpenAI Evals

Evaluation framework

GitHub

LM Evaluation Harness

Comprehensive benchmarking

GitHub

Autoresearch

Karpathy’s autonomous ML experiment framework — design, run, and evaluate 100+ experiments overnight on one GPU

GitHub

🚀 Quick Start Recommendations

🟢 Beginner Friendly

Text Generation: LM Studio + Qwen 3-4B
Image Generation: Z-Image-Turbo Demo via Hugging Face Spaces
Code: Qwen3-Coder-3B via LM Studio

Z-Image-Turbo Space

🔥 Production Ready

Text: Claude 4.5 or Gemini 3 APIs
Images: FLUX Pro API
Video: Veo 3.1 or Seedance 2.0 APIs

🏠 Self-Hosted

Text: vLLM + Qwen 3-14B
Images: Qwen-Image and Qwen-Image-Edit locally
Audio: Kokoro TTS locally

🤖 AI Tools & Models Directory

Language Processing

🤖 Language Models

📖 Open Source Models

🔒 Closed Source Models

🖥️ Model Running Applications

Image Generation

Video Generation

Audio Processing

Computer Vision

3D Model Generation

AI Development Tools

💻 AI Coding Assistants

🔧 Fine-tuning Platforms

☁️ Model Deployment

🤖 AI Orchestration

📊 Vector Databases

🧩 Model Context Protocol (MCPs)

🔗 Graph Databases

📈 Evaluation Tools

🚀 Quick Start Recommendations

🟢 Beginner Friendly

🔥 Production Ready

🏠 Self-Hosted

New York University