I stopped paying for ChatGPT after I installed this free local model on my phone www.makeuseof.com/stopped-paying-for-chatgpt-after-i-installed-free-local-model-on-my-phone/ I run Gemma 4 locally on my iPhone 15 Pro Max My phone out-AI’d my MacBook Gemma 4 handles the basics better than you’d expect Most of my questions never needed a supercomputer Gemma
Seguir leyendoEtiqueta: local
Un asistente educativo en tu propio ordenador
La actualidad reciente ha mostrado que en cualquier momento una IA puede fallar, o puede ser desconectado. Por este motivo es importante saber que hay alternativas que no dependen de la disponibilidad de servicios estadounidenses. Aquí hablamos de IAs instalados en tu propio ordenador. En otra contribución hablamos de Mistral,
Seguir leyendoAvec DiffusionGemma, Google optimise l’inférence locale
Avec DiffusionGemma, Google optimise l’inférence locale – Le Monde Informatique www.lemondeinformatique.fr/actualites/lire-avec-diffusiongemma-google-optimise-l-inference-locale-100450.html
Seguir leyendoSnapOtter: Self-Hosted Image Processing
The self-hosted image editor nobody talks about What SnapOtter is and why it replaced cloud tools for me SnapOtter | Self-Hosted Image Processing snapotter.com/ 50+ image tools. One Docker container. Resize, compress, convert, remove backgrounds, upscale, OCR, and more. Open source. Fully offline. Runs on your network.
Seguir leyendoComfy: Professional Control of Visual AI
Comfy — Professional Control of Visual AI comfy.org/ Professional Control of Visual AI. Comfy is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. Comfy Desktop Run on your hardware. Free forever. The full ComfyUI engine — open source, fast, extensible,
Seguir leyendoI stopped fighting LM Studio’s model UI and switched to Ollama — setup took minutes instead of hours
I stopped fighting LM Studio’s model UI and switched to Ollama — setup took minutes instead of hours www.makeuseof.com/stopped-fighting-lm-studios-model-ui-switched-ollama-setup-took-minutes/
Seguir leyendoGoogle étend l’IA agentique aux PC avec Gemma 4 12B
Google étend l’IA agentique aux PC avec Gemma 4 12B – Le Monde Informatique Pour accompagner les utilisateurs désirant exécuter des workflows d’IA agentique en local, Google avance Gemma 4 12B. Une avancée prometteuse, mais qui se heurte aux contraintes matérielles des postes de travail d’entreprise, ainsi qu’aux défis de
Seguir leyendoMy local LLM felt unfinished until I put a proper interface in front of it: OpenWedUI
My local LLM felt unfinished until I put a proper interface in front of it www.makeuseof.com/local-llm-felt-unfinished-until-put-proper-interface-in-front-of-it/ Ollama is great… for developers I want something prettier Setting up Open WebUI is super easy Docker pretty much makes it ready to go You can access it from any device Yes, even when
Seguir leyendoI stopped using OpenClaw – this is the better agent that the mainstream hasn’t caught up to yet
I stopped using OpenClaw – this is the better agent that the mainstream hasn’t caught up to yet www.makeuseof.com/stopped-using-openclaw-better-agent-mainstream-hasnt-caught-up/ Hermes beats OpenClaw in the ways that actually matter Do more, with fewer tokens Cool things I’ve done with Hermes Hermes, fix my life, no mistakes What to do if you’re
Seguir leyendoI built a private LLM on my home PC using a USB drive — it only knows what I put on it
I built a private LLM on my home PC using a USB drive — it only knows what I put on it www.makeuseof.com/built-private-llm-on-home-pc-using-usb-drive-only-knows-what-put-on-it/ Privacy risks of cloud processing Your data is never as safe as you think it is when you use the cloud Running local models with external storage
Seguir leyendo