Guozhen AI English hub
AI model tests, coding agents and practical AI tutorials
English field notes for readers in North America, Europe, and beyond: large models, AI agents, AI tools, Codex-style workflows, Claude Code, local LLMs, benchmarks, and practice resources.
Original Field Notes
View all field notes
Gemma 4 12B Local Agent Test: Running a Multimodal Model on a Laptop
A hands-on Gemma 4 12B test with Ollama and DeepLocals, covering local deployment, inference speed, RAG over local files, Word export with citations, and multimodal document understanding.
Read field note
2026-06-05 · 35 visuals
MiniMax M3 Coding Benchmark: Testing It Against GPT-5.5 and DeepSeek-V4
A hands-on MiniMax M3 benchmark across three coding-agent tasks: an Excel analytics web app, a Three.js smart factory scene, and a screenshot-to-HTML UI recreation, compared with GPT-5.5 and DeepSeek-V4.
2026-06-03 · 19 visuals
DeepSeek-V4 and MinerU for Scanned PDF RAG: A Practical Local Knowledge Base Test
A screenshot-rich test of using MinerU with DeepSeek-V4 inside DeepLocals to parse scanned PDFs, preserve formulas, retrieve local documents, and combine private files with external academic sources.
2026-06-02 · 24 visuals
I Finally Found Free Tokens for MyClaw: Qwen3.6-35B Works Directly (Tutorial)
A tutorial-style MyClaw field note showing how Qwen3.6-35B can run through iFlytek SparkDesk MaaS free API quota for coding and data-analysis workflows.
2026-05-31 · 29 visuals
I Tested Qwen3.7-Max Against Claude Opus 4.8 and DeepSeek-V4. The Result Surprised Me.
A Qwen3.7-Max benchmark against Claude Opus 4.8 and DeepSeek-V4 on an AI agent task, with screenshots and practical ranking notes.
Popular Tutorials
Coding Agent
Claude Code Guide
Read repositories, edit files, run tests, and use terminal agents for real engineering work.
AI Coding
Cursor Alternatives
Compare AI coding tools for builders who need IDE help, repo agents, and team workflows.
Command Line
Gemini CLI Guide
Use a command-line AI assistant for coding, reading files, and lightweight automation.
Local AI
Local LLM with Ollama
Understand local model setup, privacy tradeoffs, hardware limits, and practical use cases.
Decision Tool
Model Selector
Pick a model by task: coding, writing, RAG, local deployment, long context, or cost control.
AI Practice and Decision Tools
AI Practice
AI Quiz Bank
Practice questions for AI agents, RAG, local LLMs, coding tools, and model basics.
Model Decisions
Benchmarks and Rankings
Compare model capability, speed, cost, context window, and practical deployment fit.
Tool Workbench
AI Tools and Calculators
Use guides, alternatives, cost calculators, and selectors before choosing an AI stack.
Common Entrypoints
Tutorials, English field notes, tool guides, calculators, quizzes, model rankings, and daily AI signals.
Latest Updates
Daily AI signal
Browse recent model releases, AI agent updates, tool changes, and industry signals by date.