edge-ai

Tag

Cards List
#edge-ai

Gemma 4 VLA Demo on Jetson Orin Nano Super

Hugging Face Blog · 2026-04-22 Cached

NVIDIA and Hugging Face publish a hands-on demo showing Gemma 4 running as a vision-language-action model entirely on the Jetson Orin Nano Super, using local STT/TTS and webcam input.

0 favorites 0 likes
#edge-ai

Soul Player C64 – A real transformer running on a 1 MHz Commodore 64

Hacker News Top · 2026-04-20 Cached

Soul Player C64 implements a real 2-layer decoder-only transformer with ~25,000 int8 parameters in hand-written 6502/6510 assembly, running entirely on an unmodified 1 MHz Commodore 64 loaded from a floppy disk. The project includes training scripts to build and quantize custom models, assemble C64 binaries, and run inference at roughly 60 seconds per token.

0 favorites 0 likes
#edge-ai

The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus

Hugging Face Daily Papers · 2026-04-18 Cached

Empirical study shows small language models achieve 100% adversarial robustness with System 1 intuition but collapse under System 2 reasoning when used as edge-native governance firewalls in decentralized autonomous organizations.

0 favorites 0 likes
#edge-ai

Cactus-Compute/needle

Hugging Face Models Trending · 2026-03-16 Cached

Cactus-Compute releases Needle, a 26M parameter distilled model from Gemini 3.1, using a pure attention architecture optimized for on-device inference and local fine-tuning.

0 favorites 0 likes
#edge-ai

Frigate with Hailo for object detection on a Raspberry Pi

Jeff Geerling · 2026-02-18 Cached

This blog post details how to set up Frigate with a Hailo AI coprocessor on a Raspberry Pi for object detection, including steps to fix a PCIe descriptor page size error. The setup works with the cheaper Hailo-8L and achieves low inference times.

0 favorites 0 likes
#edge-ai

Introducing Gemma 3 270M: The compact model for hyper-efficient AI

Google DeepMind Blog · 2025-10-23 Cached

Google introduces Gemma 3 270M, a compact 270-million parameter model designed for efficient on-device AI with strong instruction-following capabilities and extreme energy efficiency (0.75% battery for 25 conversations on Pixel 9 Pro).

0 favorites 0 likes
#edge-ai

lucataco/moondream2

Replicate Explore · 2026-05-22 Cached

moondream2 is a compact vision language model designed for efficient edge device inference, with benchmark results and usage instructions provided.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback