Local LLMs
Local LLMs are language models that run directly on your own hardware — a laptop, a PC with a GPU or a home server — with no cloud, no subscriptions and no data leaving your machine. Ollama, llama.cpp and LM Studio, plus quantized GGUF builds of Llama, Qwen and Gemma, make it possible even on a decade-old graphics card. Here is all our coverage of running AI locally: guides, hardware tests, quantization and privacy.
Your own cloud LLM: how to fit within 16 GB of VRAM
Spending on language model APIs is rising rapidly. Developers are increasingly looking for an alternative — and finding it in self-hosted solutions that fit on a…
AI code review without the cloud: how Ollama is changing the approach to local development
Developers showed how to run a full AI code review directly on a local machine—without cloud services, API keys, or subscriptions. Ollama and local models make this…
Gemini 3.1 Flash-Lite: Google bets on low-cost, fast AI
Google has unveiled Gemini 3.1 Flash-Lite, the fastest and most cost-efficient model in the Gemini 3 lineup. The company is signaling to the market: the era of…
llm-checker: a utility that shows which LLMs your hardware can run
NVIDIA Nemotron 2 Nano 9B: a new standard for sovereign AI in Japan
DGX Spark with Qwen3: the NVIDIA test that didn't tell the whole story
How to Train AI on Human Preferences: A Guide to DPO and QLoRA
Diffusion language models challenge GPT with a 892-token speed record
Researchers have introduced a 100-billion-parameter diffusion model that runs faster than traditional solutions. This opens an alternative path for AI development.
Free alternative to Claude Code: test drive of a local Qwen3 solution
Can a free solution replace a paid coding tool? Claude Code from Anthropic is powerful, but expensive.
Coding Without the Curse: How to Tame Neural Networks and Not Go Broke on Subscriptions
DeepSeek vs GPT-5: China's tech market turned into a gladiatorial arena
Found. Alive: Why AI Succeeds Where Thousands of Volunteers Fail
Pixel 10a: Google stumbles, but will AI save the budget segment?
Claude Code: 20 minutes of silence that made developers remember their coffee
Imagine a typical morning for a modern developer. The coffee hasn't cooled yet, the terminal is open, and your trusted Claude Code is ready to generate dozens of…
SQL without analysts: how ecom.tech made local LLMs write queries
Every time a manager needs sales data for last Thursday, somewhere in the world one analyst quietly despairs. At ecom.tech, they decided to put an end to it.