Google's new open source Gemma 4 12B analyzes audio, video — and runs entirely locally on a typical 16GB enterprise laptop

For enterprise leaders aiming to decentralize their AI workloads, Gemma 4 12B offers a rare combination of edge-friendly efficiency and frontier-class reasoning.
Digit

Encoder-Free AI explained: The architecture behind Google’s Gemma 4 12B

A vast majority of multi-modal AI systems function as a relay race. For example, an image will come in through the Vision Encoder, be transformed into a language the Language Model understands and ...
VentureBeat

Karpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving markdown library maintained by AI

AI vibe coders have yet another reason to thank Andrej Karpathy, the coiner of the term. The former Director of AI at Tesla and co-founder of OpenAI, now running his own independent AI project, ...
GIGAZINE

The 'LLM Architecture Gallery' illustrates the architectures of various large-scale language models such as GPT, Llama, and Grok.

While various large-scale language models exist, such as OpenAI's GPT series, xAI's Grok, and Meta's Llama, the ' LLM Architecture Gallery,' which illustrates the structures of these models, is ...

Google drops Gemma 4 12B: A game-changing AI that runs on your laptop

India, June 7 -- Google has announced the launch of Gemma 4 12B, a dense multimodal model featuring a unified, encoder-free architecture.
XDA Developers on MSN

I ran my local LLM for hours and watched it get dumber in real time

The AI was smarter than the person setting it up ...
Semiconductor Engineering

NPU Acceleration For Multimodal LLMs

Transformer-based models have rapidly spread from text to speech, vision, and other modalities. This has created challenges for the development of Neural Processing Units (NPUs). NPUs must now ...