Skip to content

On-device AI

AI on phones, laptops and edge devices: small models, local inference and edge chips.

Latest picks

1–20 of 23

Nov 13Friday

Hacker News front page

Edge0 open-sources Edge0-145B and Edge0-120B for local inference on personal computers

Edge0 released Edge0-145B, Edge0-120B, a unified inference framework and deployment tools, all open source, so coding, reasoning and agent tasks can run on supported personal computers. Internal tests report Edge0-145B at 29GB peak memory, 1,100+ tokens/s prefill and 80+ tokens/s decode. Expert matrix sharing, layered loading and CPU/GPU co-execution cut the runtime load.

Why it matters: Edge0 designed the model architecture and inference engine together, using expert matrix sharing, layered loading and heterogeneous scheduling to cut memory use and data movement for local runs.

TechCrunch · AI

How removing Jensen Huang as Nvidia CEO could hurt the AI industry: five areas

TechCrunch lays out five areas that could be affected if Jensen Huang is removed as Nvidia CEO: open-weight models, agent safety, how people view AI tools, AI PCs and data center financing. The piece argues Huang has been an important advocate for these directions inside the industry.

Why it matters: Huang pushed open-weight models, agent safety and data center financing, and the article asks what loses its main industry advocate if he goes.

Nov 4Wednesday

The Verge · AI

Apple bets on AI across its own and third-party tech to grow revenue

Apple turns AI use into revenue through hardware sales, a cut of third-party AI app subscriptions, and planned paid tiers of its own AI services. Last quarter's capital expenditure was $2.2 billion, against $77.3 billion for Amazon and $51.4 billion for Alphabet; those figures cover total capex, not AI alone.

Why it matters: Apple makes money from AI through hardware, app subscription cuts and paid tiers of its own services, while spending far less on capex than peers building infrastructure.

Nov 3Tuesday

Google Blog · Gemini

Google Recaps October 2026 AI Updates, Covering Gemini 4 and Genie 4

Google's October 2026 AI recap covers the global rollout of Gemini 4 Argon, the announcement of Gemini 4 Carbon, and the world model Genie 4. Argon goes out worldwide while Carbon stays in limited testing.

Why it matters: Google is running Argon's global release and Carbon's limited test on separate tracks, so the two frontier models differ in access and safety-testing stage.

Oct 31Saturday

The Verge · AI

Sam Altman says RAM belongs in data centers, not personal computers

On the Cheeky Pint podcast, OpenAI CEO Sam Altman said tight RAM supply should go first to raising cloud utilization. Spreading limited memory across personal computers is not ideal, he said.

Why it matters: Altman uses low memory utilization on personal computers to argue for concentrating RAM in the cloud, as DRAM supply stays constrained.

Oct 29Thursday

Google Blog · Gemini

Google and XREAL launch XREAL AURA, a wired Android XR glasses for work, video and games

Google and XREAL launched XREAL AURA, a wired XR headset running Android XR. Gemini can read the real-world view and on-screen content and help with it. The glasses weigh under 95 grams with a 70-degree field of view, connect by cable to a portable compute module, support multi-window apps and USB-C laptop screen mirroring, and Gemini can highlight objects in view.

Why it matters: AURA puts Gemini into the real-world view and laptop windows, so users can ask about what is in front of them while working across apps.

The Decoder

Google opens Android dev environment to third-party AI agents, launches new Gemini API

At this year's Android Dev Summit, Google introduced a BYOA feature for Android Studio Rabbit 2 and released a new API for connecting on-device agents and apps.

Why it matters: Google is letting third-party coding agents into Android Studio and opening app tool-call interfaces, so agents can use dev tools and app features directly.

Oct 21Wednesday

AI HOT · Products

Perplexity Computer now runs fully locally on Mac, no cloud inference needed

Perplexity CEO Aravind Srinivas says Perplexity Computer can now run entirely on a Mac, with no cloud inference or WiFi. Both the model and the agent run on the machine, and it can operate native Mac apps and local files, so sensitive data doesn't have to leave the device. The feature is available now in the Perplexity Mac app.

Why it matters: Running the model and agent on the Mac itself means sensitive data stays local while it works with native apps and files.

Oct 16Friday

AI HOT · Products

NVIDIA RTX Spark laptops go on sale today, up to 128GB unified memory

NVIDIA's RTX Spark laptops went on sale worldwide today, with up to 128GB of unified memory and 1 petaflop of FP4 AI performance, starting at $2,599. The machines pair a Blackwell RTX GPU with a Grace CPU and CUDA, run large language models and AI agents locally, and add agent permission controls plus inference serving over a home network.

Why it matters: RTX Spark puts local model running, coding and testing inside a Windows laptop, cutting how much the dev loop depends on cloud test environments.

The Verge · AI

Meta and Apple team up to run Muse AI models better on Mac

Meta released Muse Spark Open with open weights and worked with Apple to run it through the latest MLX framework on two Apple M5 Ultra Mac Studios. Meta says the model is natively multimodal, has 816 billion total parameters, and handles long-horizon tasks, complex software engineering and multi-step reasoning. The two companies worked together for months, and Apple published a technical article covering MLX, Muse Spark Open and two other open models.

Why it matters: A months-long Meta and Apple collaboration lands as model and framework tuning that runs a large open-weight model on two desktop machines.

Hacker News front page

Meta releases Muse Spark Open weights, runs locally on two Mac Studios

Meta released the Muse Spark Open model weights with native multimodal support, 816B total parameters, 42B active parameters and a 1M-token context window, aimed at coding and agent tasks. The weights run locally on two Mac Studios.

Why it matters: Meta's open weights and two-Mac-Studio local run put coding and multimodal agent workflows on the desktop.

AI HOT · Models

Black Forest Labs releases FLUX 3 Image Klein, a 5.6B open-weight image model

Black Forest Labs released FLUX 3 Image Klein, a 5.6B open-weight model that handles text-to-image, image editing and multi-reference generation with up to 10 reference images. INT8 quantization lets it run on devices with as little as 8GB of VRAM, lowering the hardware bar for local image generation and editing.

Why it matters: FLUX 3 Image Klein runs on 8GB of VRAM with INT8 quantization, which lowers the hardware bar for local image generation and editing.

AI HOT · Models

NVIDIA releases open Nemotron 3.5 Super VL and two Bolt edge models

NVIDIA released Nemotron 3.5 Super VL and two Bolt edge models, covering agent deployment from enterprise servers down to local devices. Super VL is a 120-billion-parameter multimodal model with open weights, datasets and training recipe; it reads images, web pages and PDFs, and can be post-trained on an organization's own data.

Why it matters: NVIDIA's open models for servers and edge devices let organizations pick a deployment tier by hardware and tune agent tasks on their own data.

Oct 13Tuesday

Hacker News front page

Apple HomeView puts Siri AI in a home hub with personal assistant and smart home control

Apple HomeView runs a Siri AI built on Apple Intelligence, combining personal context, knowledge questions and smart home control into a home assistant. The device has an A18 chip and a 7-inch Liquid Retina display and can recognize up to six users. Reaching personal content requires a paired iPhone or iPad on the same Wi-Fi, recently unlocked, plus face recognition.

Why it matters: Apple HomeView brings a personalized assistant to a shared household device, using face recognition and paired-device conditions to separate personal content from what guests can use.

Hacker News front page

Anthropic study: AI models may self-replicate without a data center

Anthropic's experiments show small AI models can complete several steps of self-replication, though a full runaway self-replicating system has not been achieved. The study ran Gemma4-26B-A4B on 15 Android TV boxes at 0.39 tokens per second, and Qwen3.5-9B deployed inference on 8 of 9 hardware types tested.

Why it matters: Anthropic tested inference deployment and end-to-end replication separately, drawing a clear line between small models adapting to unfamiliar hardware and completing the whole replication chain.

Oct 8Thursday

AI HOT · Products

NVIDIA and Microsoft launch RTX Spark, make Windows agent container MXC generally available

NVIDIA and Microsoft launched RTX Spark for Windows laptops and compact desktops. Microsoft also said Microsoft Execution Containers (MXC) is generally available, letting agents run safely and continuously in the background under operating system control.

Why it matters: NVIDIA and Microsoft are putting local AI hardware and an agent execution container into Windows, so model inference and background agent runs sit in the same desktop environment.

Oct 7Wednesday

Hacker News front page

Strands releases open-source decision model Strands Decider 2B

Strands released Strands Decider 2B, aimed at local experimentation and agent workflows, with code, weights, training data and scripts open on GitHub and Hugging Face.

Why it matters: Its examples check the grounds for parameters and the timing of a call before a tool runs, putting low-cost decisions into an agent's clarification flow.

Google DeepMind

Google DeepMind releases EmbeddingGemma 2 for on-device multimodal embeddings

Google DeepMind released EmbeddingGemma 2, built on the Gemma 4 architecture, which maps text, code, images, video and audio into one shared embedding space. The model has 740 million parameters, ships under the Apache 2.0 license, and supports an 8K token context window for fully offline cross-modal search and RAG. Text-only tasks need just 270M parameters, and output vectors can be cut from 768 dimensions to 128.

Why it matters: EmbeddingGemma 2 runs cross-modal retrieval on local devices, so text, image, audio and video search never has to send data to the cloud.

Oct 5Monday

Hacker News front page

RemoveMacAI turns off Apple Intelligence on macOS 27 and reclaims model storage

RemoveMacAI can turn off Apple Intelligence on macOS 27, remove downloaded models and block them from downloading again, and every change can be undone. It works through user-approved configuration profiles and Apple's asset services, so System Integrity Protection stays on. Features that rely on on-device models stop working, and macOS itself schedules the actual deletion of the model files.

Why it matters: The tool disables system AI through reversible profiles and blocks model re-downloads, freeing storage while turning off features that depend on on-device models.

Aug 12Wednesday

Google DeepMind

Google DeepMind releases SL2T sign language-to-text model, first in Pixel 11 Gboard and Live Transcribe

Google DeepMind released SL2T, a multilingual sign language-to-text model, bringing sign language AI into consumer products for the first time. On Pixel 11, Gboard and Live Transcribe support American Sign Language (ASL) to English dictation, with more devices and languages to follow.

Why it matters: Google DeepMind put its multilingual sign language to text model SL2T into Gboard and Live Transcribe on Pixel 11, supporting American Sign Language dictation in English.