Local AI
Stories from Local AI come first, newest first, then stories from connected topics (llama.cpp, Ollama, NVIDIA RTX Spark, on-device AI, AI Models, Hugging Face), each labelled with where it comes from. This view is not indexed by search engines.
Opera Puts Local AI in Its Browser, Giving Sites 3 Opt-In WebAI APIs
Opera has begun shipping local AI models in Opera One as an opt-in WebAI preview, so websites and extensions can run AI on the user's own device.
Just in
Latest
AMD Launches Its Next Ryzen AI Halo Developer Platform, With Up to 192GB of Memory for Running Large AI Models Locally
AMD has launched its next Ryzen AI Halo developer platform, with the Ryzen AI Max+ PRO 495 and up to 192GB of memory for running big AI models locally.
NVIDIA Readies Its RTX Spark Laptops for Local AI Agents With a New Open Model, Nemotron 3.5 Bolt
NVIDIA's open Nemotron 3.5 Bolt model for local AI agents on RTX Spark PCs arrives 15 October, and its PAIR router leaves beta today.
LightOn Releases ColGrep-Agent-2B, an Open Local Code-Search Agent That It Says Cuts Claude Code’s Tokens by a Third
LightOn's open 2B-parameter ColGrep-Agent searches code locally for coding agents; it says Claude Code used 34% fewer API tokens than with grep.
NVIDIA’s Jetson Kiosk Demo: A Coding Agent Puts a Vision Model on the Device
An NVIDIA tutorial shows OpenAI's Codex coding agent turning a Jetson Orin Nano into a self-starting kiosk that captions a live webcam feed with Google's small Gemma 4 E2B model, running on the device. What the demo shows, what "No Mac required" means, and why local inference matters.
Personalised RAG, Memory and AI Agents: How a Hybrid Assistant Works
Update, 2 Nov 2026: This explainer has been revised. We removed an unsupported claim about measured gains from chatbot memory features, softened claims that RAG systems do...
Ollama Just Made Apple Silicon the Fastest Platform for Local AI
Ollama Just Made Apple Silicon the Fastest Platform for Local AIFor years, running large language models locally meant one thing: NVIDIA GPUs. CUDA was the standard, GeForce...
GGUF, AWQ, GPTQ, EXL2 and FP8: LLM Quantization Formats Compared
LLM quantization is what makes it possible to run large language models on ordinary hardware: it stores a model's weights at lower precision so they take far...
Running Vision LLMs Locally: LLaVA, BakLLaVA & Beyond (2026 Guide)
Running Vision LLMs Locally: LLaVA, BakLLaVA & Beyond (2026 Guide)
How to run vision LLMs such as LLaVA to analyse images with AI—completely offline, completely privateIntroduction: Why Vision...
Prompt Engineering for Self-Hosted LLMs: Getting the Most from Small Models
Prompt Engineering for Self-Hosted LLMs: Getting the Most from Small ModelsRunning large language models locally has never been more accessible. With models like Phi-3, Llama 3.2, and...
Tencent Agent Trains Two Open Protein Models, HyInv and HyPLM
Tencent Hunyuan has released HyInv and HyPLM-Flash, two protein models it says its Hyra 2.0 research agent trained, with open weights under an MIT licence.
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.