New 3h31m video on YouTube: "Deep Dive into LLMs like ChatGPT" This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental

I'm a huge fan of LM Studio and encourage all to use it for its features (runs on your desktop, great UI, easy to use, improves privacy). Since it makes open-source models a breeze to use it can also help ensure the world is not dominated by a couple large oligarch closed AIs.

🤯 Gemma 3 is available on Ollama! Multimodal is here for Gemma. 1B (text-only): ollama run gemma3:1b 4B: ollama run gemma3:4b 12B: ollama run gemma3:12b 27B: ollama run gemma3:27b

Ollama v0.6.3 is here! Happy Friday. Google Gemma 3 now runs faster and more efficiently!

TL;DR: we are excited to release a powerful new open-weight language model with reasoning in the coming months, and we want to talk to devs about how to make it maximally useful: openai.com/open-model-fee… we are excited to make this a very, very good model! __ we are planning to

Llama 4 models are here! They are quite large with the smallest one being 109B. Support might take a little bit to bring up, but be sure we are on it! 🦾

.ollama is playing with AI at Meta Llama 4 Scout! 🤯 a perfect opportunity to test Ollama's giant super computer ✈️✈️✈️

All media channels, digital platforms and individuals are advised to refrain from live coverage or real-time reporting of defence operations and movement of security forces. Disclosure of such sensitive or source-based information may jeopardize operational effectiveness and

No cloud? No problem. @CristianoAmon shared at #COMPUTEX2025: The new Docker Model Runner SDK lets you build and run gen #AI models on-device, now optimized for Snapdragon X Series. bit.ly/3FlLX5B

just one more cup before ollama gets ready

The new reasoning model from OpenAI now runs directly on Snapdragon platforms. This is the first time a model from OpenAI has been deployed on-device—enabled by our Qualcomm AI Stack and heterogeneous compute. Available via Hugging Face and Ollama. qualcomm.com/news/onq/2025/…

The heart of your computer just leveled up. OpenAI now runs directly on flagship Snapdragon processors. Learn more: qualcomm.com/news/onq/2025/…

A major win for developers building on-device AI applications. Congrats yags and the LM Studio team on pushing the boundaries of local inference and model optimization. Excited to see what the community builds next!

Collaborating with NEXA AI has been incredible. We’ve unlocked blazing-fast NPU performance across multiple platforms powered by just two lines of code. The era of seamless, on-device AI is here. Get ready for what’s next!

Snapdragon Alex Katouzian Don McGuire Cristiano R. Amon Clare Conley Greg AnythingLLM AnythingLLM is making huge tides with the Snapdragon 8 Elite Gen 5 & #SnapdragonXSeries X2 Elite!! #SnapdragonSummit #ShotonSnapdragon Snapdragon Alex Katouzian Don McGuire Cristiano R. Amon Clare Conley Greg

Qualcomm IBM Snapdragon Excited to bring Day-0 support for IBM Granite 4.0 on Qualcomm Hexagon NPU — and seamlessly across GPU & CPU. Big thanks to Qualcomm for the partnership and the powerful Snapdragon chips that make on-device AI real.

Thank you to the teams at NEXA AI and IBM for partnering with us to deliver day-0 support for models on NPU. Enterprise developers can now rapidly test and deploy their applications across CPU, GPU, and NPU, maximizing efficient use of our @snapdragon X Series PCs.

This week in #AI: 🔵 Qualcomm President and CEO Cristiano R. Amon explains how the edge is essential to what’s next in AI: bit.ly/3KDfHNr 🔵 Forbes: Snapdragon 8 Elite Gen 5 and Snapdragon X2 Elite usher in the age of agentic AI: bit.ly/4gQGt13 🔵 IBM

Qualcomm Cristiano R. Amon Forbes Snapdragon IBM Proud to support IBM Granite 4.0 on Snapdragon NPUs from day-0 with Qualcomm. On-device AI, deployment-ready with us.

Sam Altman recently said: “GPT-OSS has strong real-world performance comparable to o4-mini—and you can run it locally on your phone.” Many believed running a 20B-parameter model on mobile devices was still years away. At Nexa AI, we’ve built our foundation on deep on-device AI