LLMs & Models Articles
Browse 527 articles about LLMs & Models.
What Is the Pencil Puzzle Benchmark? The Test That Measures Pure Multi-Step Logical Reasoning
Pencil Puzzle Bench tests constraint satisfaction problems with no training data contamination. GPT-5.2 scores 56%. Chinese models score under 7%.
What Is the SWE-Rebench Benchmark? How Decontaminated Tests Expose Chinese Model Inflation
SWE-Rebench uses fresh GitHub tasks that models haven't seen in training. Chinese models that match Western scores on SWE-bench drop significantly here.
Gemma 4 E2B vs E4B: How to Run a Multimodal AI Model on Your Phone
Gemma 4's edge models support audio, vision, and function calling in under 4B parameters. Here's how to run them locally on Android and iOS devices.
How to Run Gemma 4 Locally on Your Phone or Laptop With the Google AI Edge Gallery
Google AI Edge Gallery lets you download and run Gemma 4 models locally on Android and iOS with no cloud connection. Here's how to set it up in minutes.
What Is Gemma 4? Google's Apache 2.0 Open-Weight Model With Native Audio and Vision
Gemma 4 ships under Apache 2.0 with native audio, vision, function calling, and thinking. Here's what makes it different from every previous Gemma release.
What Is Microsoft MAI Transcribe 1? The Speech Model That Outperforms Whisper and Gemini Flash
MAI Transcribe 1 achieves best-in-class accuracy across 25 languages and beats Whisper, Gemini Flash, and GPT Transcribe on word error rate benchmarks.
What Is Anthropic's Prompt Caching and Why Does It Affect Your Claude Subscription Limits?
Anthropic uses prompt caching to reduce compute costs. When third-party tools break caching, your session limits drain faster. Here's the technical explanation.
Gemma 4 vs Qwen 3.5: Which Open-Weight Model Should You Use for Local AI Workflows?
Compare Gemma 4 and Qwen 3.5 on performance, size, context window, and local deployment to find the best open-weight model for your agentic workflows.
What Is Google Gemma 4? The Apache 2.0 Open-Weight Model With Native Audio and Vision
Gemma 4 is Google's first truly open-source model family under Apache 2.0. It runs on phones, supports audio and vision, and rivals closed-source models.
What Is Qwen 3.5 Omni? Alibaba's Multimodal Model That Builds Apps From Your Camera
Qwen 3.5 Omni handles text, image, audio, and video and can build a website from a camera description. Here's what it does and how to use it.
What Is Qwen 3.6 Plus? Alibaba's 1M Token Agentic Coding Model Explained
Qwen 3.6 Plus is Alibaba's frontier-level model built for real-world agents, agentic coding, and multimodal vision with a 1M token context window by default.
What Is Gemma 4's Apache 2.0 License? Why It Matters More Than the Model Itself
Gemma 4 ships under Apache 2.0—not a custom restricted license. Here's what that means for commercial use, fine-tuning, and building on top of Google's models.
How to Run Claude Code for Free Using Ollama and Open Router
Learn two ways to use Claude Code without paying for Anthropic tokens: run open-source models locally with Ollama or route through Open Router's free tier.
How to Run Gemma 4 Locally with Ollama: Step-by-Step Setup Guide
Learn how to download and run Google's Gemma 4 locally using Ollama, check VRAM requirements, and connect it to Claude Code for free.
MAI Transcribe 1 vs OpenAI Whisper vs Gemini Flash: Which Speech Model Wins?
Compare Microsoft MAI Transcribe 1, OpenAI Whisper, and Gemini 3.1 Flash on accuracy, noise handling, and multilingual support.
How to Use Open Router Free Models With Claude Code to Cut AI Costs by 99%
Configure Claude Code to route through Open Router's free model tier instead of Anthropic's paid API. A step-by-step guide with the exact settings.json setup.
Open-Source vs Closed-Source AI Models: Which Should You Use for Agentic Workflows?
Compare open-weight models like Gemma 4 and Qwen 3.6 against closed models like Claude Opus and GPT-5.4 for agentic coding and automation tasks.
Why You Should Use an Agentic Harness With Qwen 3.6 Plus (Not Just Chat Mode)
Qwen 3.6 Plus performs dramatically better inside an agentic harness than in chat mode. Here's why and how to set it up with OpenCode.
Qwen 3.6 Plus vs Claude Opus 4.6: Which Model Is Better for Agentic Coding?
Compare Qwen 3.6 Plus and Claude Opus 4.6 on agentic coding benchmarks, context window, multimodal support, and real-world task performance.
What Is Microsoft MAI Transcribe 1? The Speech Model That Beats Whisper and Gemini
MAI Transcribe 1 is Microsoft's new speech recognition model that outperforms Whisper, Gemini Flash, and Scribe V2 across 25 languages.