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.
Microsoft bets on in-house AI models to cut costs
Microsoft has joined the trend of cutting AI spending and plans to significantly expand the use of its own models, reducing its reliance on third-party providers.
Microsoft launched Foundry Managed Compute: thousands of Hugging Face models with one click
Microsoft combined Azure Foundry with the Hugging Face catalog: thousands of open models now deploy in the cloud with one click, with enterprise security and…
Gemma 4 Parses PDFs as Images: Zero-Shot Approach Without OCR and Cloud
Google's multimodal Gemma 4 processes any PDF—scans and digital documents—without an OCR pipeline: pages are converted to images and passed directly to the model.
NVIDIA TensorRT now scales generative AI inference across multiple GPUs
7 Best Coding Models for Local Deployment in 2026: Qwen, DeepSeek, and More
Amazon SageMaker AI adds support for P-EAGLE to accelerate LLM inference in parallel
Qualcomm chief: AI agents will become the new apps, 40 devices on the way
Google DeepMind released DiffusionGemma — an open 26B MoE model with 4x faster generation
Google DeepMind released DiffusionGemma, an experimental 26B-parameter open model that uses text diffusion instead of autoregression — generation is up to 4x faster…
Google released Gemma 4 12B: 150 million downloads, runs on a laptop with 16 GB of VRAM
Google DeepMind has released Gemma 4 12B — a compact open model that runs locally with 16 GB of VRAM, marking 150 million downloads for the series under the Apache…
How to build an AI agent in Google Colab without frameworks: a tutorial with memory and MCP
DeepSeek released DSpark — a framework that speeds up generation on DeepSeek-V4 by 57–85%
Liquid AI released LFM2.5-230M: 213 tokens/s on Galaxy S25 and support for llama.cpp
Local AI agent instead of sysadmin: autonomous server log analysis
Russia's Digital Ministry registers first AI assistant for government officials
Russia's Digital Ministry has registered the first AI assistant for civil servants in the national software registry—a tool designed to support decision-making and…
2026 TTS Models Comparison: From Commercial to Open Source
In 2026, choosing a TTS model depends on three factors: sound quality, processing latency, and cost. Commercial solutions win on naturalness, open models on control…