详细内容
The Most Comprehensive Resource for AI Students, Developers, and Researchers
Tools and Practical Learning Resources to Pioneer the Future of AI.
Best LLMs for CodingFind Models You Can Run
Learners
Introductory Courses Learning Roadmap AI/ML Blog
Developers
Machine Learning Courses VRAM Calculator Local LLM Directory
Researchers
Fine-Tuning Calculator Advanced Courses Pioneering Courses
Kerb
Open-source LLM developer toolkit
Production-ready Python utilities for building LLM applications. Modular components for chunking, embeddings, RAG, agents, and more.
pip install kerb
Local LLM Performance Rankings
| Model | Overall Rank | Coding Rank | VRAM (Q4) |
|---|---|---|---|
| DeepSeek-R1 671B | 🥇1 | 🥈2 | ~ 358.80 GB |
| Kimi K2-Instruct | 🥈2 | 12 | ~ 523.06 GB |
| DeepSeek-V3.1 | 🥉3 | 10 | ~ 360.78 GB |
| DeepSeek-V3 671B | 4 | 4 | ~ 359.44 GB |
| GPT-OSS 120B | 5 | 🥇1 | ~ 73.46 GB |
| GLM-4.5 | 6 | 14 | ~ 258.16 GB |
| GLM-4.5-Air | 7 | 13 | ~ 79.24 GB |
| Qwen3 235B A22B Thinking | 9 | 15 | ~ 161.13 GB |
VRAM Calculator
Estimate GPU memory requirements for your self-hosted LLMs
Instantly see if your architecture will fit on your hardware. Avoid out-of-memory errors before you even start training.
Trusted by AI Students and Professionals
Courses, references, and tools are utilized and cited by top universities and industry-leading tech companies worldwide.
Show More
Popular Guides
How To Build A Large Language Model
Acquire the engineering skills to construct, train, and optimize sophisticated large language models.
Approx. 80 hours
Programming and Deep Learning
Advanced Transformer Architecture
Master the theory, mathematics, and implementation of advanced Transformer architectures for modern LLMs.
Approx. 30 hours
Deep Learning & Python Proficiency
LangChain for Production-Ready LLM Applications
Develop and operationalize complex, scalable LLM applications using advanced LangChain features and best practices.
Approx. 32 hours
Python & Basic LangChain
Python Programming Fundamentals
Acquire the core Python skills needed to write clear, functional code and begin your programming path.
Approx. 20 hours
No prior programming experience.
Practical Quantization for Large Language Models
Implement LLM quantization techniques (PTQ, QAT, GPTQ, GGUF) to reduce model size and improve inference speed.
Approx. 15 hours
LLM Fundamentals & Python
Build and train fundamental deep learning models using PyTorch's core features like tensors, autograd, and neural network modules.
Approx. 18 hours
Basic Python & ML knowledge
Python for LLM Workflows: Tooling and Best Practices
Build and manage LLM applications using Python, LangChain, LlamaIndex, and essential development practices.
Approx. 18 hours
Intermediate Python skills
Build, optimize, and deploy complex deep learning models using PyTorch's advanced capabilities.
Approx. 36 hours
Intermediate PyTorch & DL concepts
Mastering Gradient Boosting Algorithms
Effectively implement, tune, and interpret advanced gradient boosting models for sophisticated machine learning applications.
Approx. 28 hours
Python & ML Fundamentals
Time Series Analysis and Forecasting
Analyze time-dependent data and build statistical forecasting models like ARIMA and SARIMA.
Approx. 15 hours
Basic Python and Pandas
RLHF: Reinforcement Learning from Human Feedback
Apply Reinforcement Learning from Human Feedback (RLHF) principles and techniques to align large language models.
Approx. 24 hours
Advanced ML & DL knowledge
Advanced Reinforcement Learning Techniques
Implement and apply advanced reinforcement learning algorithms to solve complex sequential decision-making challenges.
Approx. 70 hours
Python, ML & RL Fundamentals
MASTERCLASS
HOW TO BUILD A LARGE LANGUAGE MODEL
30 Chapters, 700+ Pages of In-Depth Content
Guide to understanding and building state-of-the-art language models
Prerequisites: Strong foundations in programming and deep learning
Recent Articles & Insights
How to Estimate LLM Time to First Token (TTFT)
Nov 28, 2025
Information on the mathematics behind estimating Time to First Token. We break down prefill dynamics, hardware scaling, and attention mechanisms to help you predict model latency without running the code.
How to Set Up OAuth for the ChatGPT Connector
Oct 21, 2025
Step-by-step guide to walk you through the exact endpoints and response specs OpenAI expects, including the undocumented OIDC location and token exchange.
Why Is No One Using Model Context Protocol (Yet)
Oct 8, 2025
The Model Context Protocol (MCP) promises to unify AI tools, saving you money on subscriptions. So why has it failed to gain traction? We'll look at the technical and market hurdles holding it back.
30 Precise Terms to Use Instead of 'AI'
Oct 6, 2025
How to stop saying 'AI' for everything. This guide gives you 30 specific machine learning terms that you can use to demonstrate proficiency.
How to Connect Claude to an MCP Server
Sep 26, 2025
Learn what the Model Context Protocol (MCP) is and follow our step-by-step guide to connect Claude to an external MCP server, giving it access to live data and powerful tools.
How To Build a MCP Server with FastAPI (FastAPI-MCP)
Sep 25, 2025
Learn to build a secure and scalable Model Context Protocol (MCP) server using the fastapi_mcp library. This step-by-step guide covers setup, authentication, and integration with AI tools like Claude, turning your APIs into a powerful toolkit for large language models.
Is Fine-Tuning Your LLM Worth It? Usually, It Isn't
Sep 18, 2025
Before you spend a fortune fine-tuning an LLM, discover faster, cheaper, and often more effective methods: prompt engineering and RAG. Learn why fine-tuning should be your last resort.
XGBoost vs. LightGBM vs. CatBoost
Sep 18, 2025
Learn which gradient boosting model to choose for speed, accuracy, and handling categorical data, with code examples and diagrams to guide you.
©2025 ApX Machine Learning
About Contact Status Advertise Terms of Use Privacy Policy
This site uses cookies to enhance your experience. Manage your preferences below.
AcceptDecline Learn More