Hacker News with Generative AI: Edge Computing

NimbleEdge AI App - First offline voice AI by running Python on-device (nimbleedge.com)
We’re thrilled to introduce NimbleEdge AI, the industry’s first fully on-device conversational assistant powered by the NimbleEdge platform. With no internet dependency, no cloud processing, and no data leaving your device, this is the future of AI: private, secure, and always accessible—even offline.

Artificial Intelligence, Software, Mobile, Privacy, Edge Computing

20 points by vkkhare 46 days ago | 6 comments

Tailscale 4via6 – Connect Edge Deployments at Scale (tailscale.com)
Tailscale lets you connect anything to anything — securely. But real-world deployments often come with messy networks: overlapping IPs, double NAT, and strict firewalls.

Networking, Security, Cloud Computing, Software, Edge Computing

120 points by tiernano 46 days ago | 38 comments

An Active Message Inspired Reconfigurable Architecture for Irregular Workloads (arxiv.org)
Modern reconfigurable architectures are increasingly favored for resource-constrained edge devices as they balance high performance, energy efficiency, and programmability well.

Reconfigurable Architectures, Computer Architecture, Edge Computing

5 points by PaulHoule 112 days ago | 0 comments

Magic Containers: What Edge Computing was meant to be (bunny.net)

Edge Computing, Cloud Computing, Containers, Networking

13 points by wahnfrieden 113 days ago | 2 comments

Coral USB Accelerator with Google's Edge TPU (coral.ai)
The Coral USB Accelerator adds an Edge TPU coprocessor to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port.

Machine Learning, Hardware, AI, Edge Computing

75 points by achristmascarl 129 days ago | 84 comments

Running DeepSeek R1 Models Locally on NPU (windows.com)
AI is moving closer to the edge, and Copilot+ PCs are leading the way. With the availability of cloud hosted DeepSeek R1 available on Azure AI Foundry, we’re bringing NPU-optimized versions of DeepSeek-R1 directly to Copilot+ PCs, starting with Qualcomm Snapdragon X first, followed by Intel Core Ultra 200V and others.

AI, Hardware, Edge Computing, Qualcomm, Intel

37 points by doomroot13 147 days ago | 15 comments

Phison aiDAPTIV+ leverages SSDs to expand GPU memory for LLM training (cnx-software.com)
While looking for new and interesting products I found ADLINK’s DLAP Supreme series, a series of Edge AI devices built around the NVIDIA Jetson AGX Orin platform. But that was not the interesting part, what got my attention was it has support for something called the aiDAPTIV+ technology which made us curious.

Generative AI, Hardware, Machine Learning, Edge Computing

5 points by homarp 152 days ago | 0 comments

NVIDIA Releases Jetson Orin Nano Super (nvidia.com)
The NVIDIA Jetson Orin Nano™ Super Developer Kit is a compact, yet powerful computer that redefines generative AI for small edge devices.

NVIDIA, Hardware, Generative AI, Edge Computing

5 points by Kylejeong21 192 days ago | 5 comments

Nvidia Jetson Orin Nano Super: The most affordable generative AI supercomputer (nvidia.com)
The NVIDIA Jetson Orin Nano™ Super Developer Kit is a compact, yet powerful computer that redefines generative AI for small edge devices.

Generative AI, Hardware, Edge Computing, AI, NVIDIA

16 points by centum 192 days ago | 4 comments

Omnivision-968M: Vision Language Model with 9x Tokens Reduction for Edge Devices (nexa.ai)

Computer Vision, Edge Computing, AI Models, Tokenization

69 points by BUFU 225 days ago | 12 comments

Transistor for fuzzy logic hardware: promise for better edge computing (techxplore.com)
Edge computing devices, devices located in proximity to the source of data instead of in large data centers, could perform computations locally. This could reduce latency, particularly in real-time applications, as it would minimize the need to transfer data from the cloud.

Edge Computing, Hardware, Fuzzy Logic

37 points by wglb 227 days ago | 5 comments

Edge Scripting: Build and run applications at the edge (bunny.net)
Lightning-fast global CDN

Edge Computing, Cloud Computing, Web Development, CDN

111 points by gnabgib 232 days ago | 86 comments

GDDR7 Memory Supercharges AI Inference (semiengineering.com)
High bandwidth and low latency are paramount for AI-powered edge and endpoints.

AI, Hardware, Memory, Inference, Edge Computing

68 points by PaulHoule 242 days ago | 34 comments

How the new Raspberry Pi AI Hat supercharges LLMs at the edge (novusteck.com)
The Raspberry Pi AI HAT+ introduces two performance options: a 13 TOPS model for $70 and a 26 TOPS model for $110, both featuring Hailo AI accelerators for high-performance machine learning tasks.

Artificial Intelligence, Hardware, Raspberry Pi, Machine Learning, Edge Computing

9 points by novusteck 246 days ago | 10 comments

Un Ministral, Des Ministraux (mistral.ai)
Introducing the world’s best edge models.

Artificial Intelligence, Edge Computing

216 points by veggieroll 254 days ago | 99 comments

Starbase: SQLite on the Edge (starbasedb.com)
Plug & Play SQLite

Databases, SQLite, Edge Computing

169 points by hunvreus 265 days ago | 47 comments

Serving 70B-scale LLMs efficiently on low-resource edge devices [pdf] (arxiv.org)
Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data.

Edge Computing, Privacy, Efficiency

248 points by simonpure 267 days ago | 58 comments

Llama 3.2: Lightweight models for edge devices (twitter.com)

AI, Edge Computing, New Releases

8 points by tosh 275 days ago | 0 comments

Edge Image Builder (suse.com)
Working at the edge introduces a number of complications not seen in a traditional data center.

Edge Computing, Cloud Computing, Software, Infrastructure

20 points by meysamazad 290 days ago | 5 comments

Show HN: Nexa SDK – Build powerful and efficient AI apps on edge devices (github.com/NexaAI)

Software, Artificial Intelligence, Edge Computing

27 points by frednoodle 292 days ago | 4 comments

Show HN: We built a knowledge hub for running LLMs on edge devices (github.com/NexaAI)