AI that runs on phones, computers and edge devices: small models, local inference and on-device chips.
Two weeks ago, we opened up Phonon, our small text-to-speech model that runs on your own device. It needs no server and no network, and what you type stays with you.
LFM3 is our new generation of Liquid Foundation Models (LFMs), built to be the starting point for specialized intelligence. It brings text, vision, audio, omni, and decision models onto one shared backbone, all in the 2B parameter range.
The AI startup Recursive is unveiling Flint, its first language model, a 40-billion-parameter MoE for local coding developed by former DeepMind researchers. It was created in four months using the company's in-house AI system, "Eureka Machine," which independently tests and optimizes architectures. Recursive has yet to prove whether this approach will actually lead to self-improving AI.
A new beginning for Windows PCs starts tomorrow with the launch of NVIDIA RTX Spark — one PC built for creators, gamers and AI agents. All are invited to celebrate with NVIDIA and partners at launch events around the world. Share Your Spark Every PC has a story.
Meta announced the Muse Spark Open AI model today, claiming that it's the "most capable US open-weight model to date." But the company also says that it's the "the first model in its class" that can "run on your desktop using two Apple M5 Ultra Mac Studios with the latest MLX framework."
NVIDIA today released Nemotron 3.5 Super VL, an open 120-billion-parameter model that delivers the fastest task completion and highest accuracy for specialized always-on agents.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
LFM2.5-24B-A2B is a 24B-parameter reasoning model with just 2B active parameters, built for fast, private agents on-device. It thinks before it answers, calls tools, and works through multi-step tasks inside popular agent harnesses.
NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative studio and a personal AI supercomputer into a single superchip.
At a Microsoft event in San Francisco on Wednesday, NVIDIA founder and CEO Jensen Huang and Microsoft CEO Satya Nadella outlined how NVIDIA and Microsoft are co-engineering hardware and software for AI agents to run on Windows PCs. NVIDIA was founded because of Windows, Huang said. Now AI agents are coming to Windows.
Today, we release two open decision models in our d1 decision model family : d1-3B and d1-omni-600M (experimental). Best decision model under 10B on the Decision Index 0.2.1: d1-3B scores 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11). Multimodal: d1-3B supports text and images, while d1-omni-600M supports text and images or text and audio
EmbeddingGemma 2 is the most capable model for on-device multimodal embeddings, natively mapping combinations of text, images, audio, and video into a unified embedding space.
In “Toward provably private learning from federated data”, we announce the next generation of our FL system, which leverages Trusted Execution Environments (TEEs) to provide verifiable and auditable guarantees for data anonymization. Gboard has adopted the system to launch next-word prediction models in English and Japanese, with stronger privacy guarantees and improved accuracy.
Local AI is becoming more useful by the token. As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more to run locally.
Hugging Face added GGUF support to transformers. Users can choose a quantised checkpoint from the Hub and pass gguf_file to from_pretrained for local generation without additional configuration.
Google Research proposed PhotoScan, a deep learning framework that estimates body fat percentage, A/G ratio and V/S ratio from ordinary 2D phone photos to predict insulin resistance.
Introducing sign-language-to-text (SL2T), our breakthrough model powering new sign language features for Deaf and hard of hearing users.
Figure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction. We face a new epoch in computing. Hardware is changing rapidly — not just faster GPUs, but a growing range of chips from different vendors, each with its own architecture and often tailored to specific AI workloads.
Google Research published an architecture attaching multi-token prediction (MTP) heads to frozen Gemini Nano v3 models, accelerating on-device inference without changing backbone weights. It has shipped with the Pixel 9 and 10 series.
Google DeepMind released Gemma 4 12B, a multimodal model for local laptop use between the edge-focused E4B and 26B MoE. Its unified encoder-free architecture feeds visual and audio inputs directly into the LLM backbone.