Ayush Pande writes about running the Cactus Compute Needle 3, a 29MB edge model, on a Raspberry Pi 5 to perform local smart home automation without a dedicated AI HAT. The model uses a unique sliceable ladder architecture that allows it to run on 2 to 20 layers, focusing on machine-level tasks like tool calling and data conversion rather than general chat. He demonstrates how to integrate it with Home Assistant via Python to control a smart plug, achieving impressive decode and prefill speeds.
- The model requires an ARMv7 or newer architecture, meaning it does not run on first-gen Raspberry Pi Zero devices.
- The author achieved a decode rate of 280.2 tokens/second and a prefill rate of 996.4 tokens/second on an 8GB Raspberry Pi 5.
- While designed for specialized tasks, the tool-calling framework is flexible enough to be extended for document analysis or Docker container management.
- The model requires an ARMv7 or newer architecture, meaning it does not run on first-gen Raspberry Pi Zero devices.
- The author achieved a decode rate of 280.2 tokens/second and a prefill rate of 996.4 tokens/second on an 8GB Raspberry Pi 5.
- While designed for specialized tasks, the tool-calling framework is flexible enough to be extended for document analysis or Docker container management.
Ashley writes about Needle 2, a 14MB function-calling LLM from Cactus Compute that converts plain English prompts into local actions on a Raspberry Pi 5 using CPU alone. Rather than acting as a general chatbot, the model is purpose-built to select from declared Python functions and fill in their arguments, running entirely offline after a one-time download. In benchmark runs, inference latency ranges from 76 to 149 milliseconds, and the model correctly refuses questions outside its declared tool set.
- Native session is ~28MB; the full Python process peaks at 43–46.4MB
- Weights and code released under Apache 2.0 on Hugging Face and GitHub
- Can be fine-tuned locally on a laptop for a specific set of tools
- Eben Upton's endorsement: "Needle 2 is rather excellent"
- Native session is ~28MB; the full Python process peaks at 43–46.4MB
- Weights and code released under Apache 2.0 on Hugging Face and GitHub
- Can be fine-tuned locally on a laptop for a specific set of tools
- Eben Upton's endorsement: "Needle 2 is rather excellent"
Simon Batt writes about Fugleramme, a Raspberry Pi 5 project by arnegiacomo that passively listens to bird calls via a USB microphone and displays hand-curated 1800s natural-history cutouts of the species it detects on an Inky e-ink display. The system runs fully offline on the Pi using BirdNET-Go for detection, deliberately avoiding generated images in favor of genuine historical illustrations.
- The mic is a lavalier with a thin cable taped under the roof and threaded in through the window
- Currently features European birds; US species are in progress
- A live demo of the creator's own device is available at their dev website
- Open-source on GitHub under the name Fugleramme
- The mic is a lavalier with a thin cable taped under the roof and threaded in through the window
- Currently features European birds; US species are in progress
- A live demo of the creator's own device is available at their dev website
- Open-source on GitHub under the name Fugleramme
This article details a project where the author successfully implemented OpenClaw, an AI agent, on a Raspberry Pi. OpenClaw allows the Raspberry Pi to perform real-world tasks, going beyond simple responses to actively controlling applications and automating processes. The author demonstrates OpenClaw's capabilities, such as ordering items from Blinkit, creating and saving files, listing audio files, and generally functioning as a portable AI assistant. The project utilizes a Raspberry Pi 4 or 5 and involves installing and configuring OpenClaw, including setting up API integrations and adjusting system settings for optimal performance.
This article discusses the choice between Jetson Nano and Raspberry Pi 5 for building a first ROS2 robot, advocating for a Raspberry Pi 5-based kit like the MentorPi M1 to bypass hardware headaches and accelerate learning.
This article details how to build a fast, offline AI chatbot using a Raspberry Pi 5, RLM AA50 accelerator card, and optimization techniques for speech recognition, natural language processing, and text-to-speech tasks.
A Raspberry Pi 5 can transform a home network into a faster, safer, and easier-to-manage system by consolidating DNS, VPN, and monitoring tools into a single, low-power machine.The author implemented Pi-hole (ad blocking & DNS), Unbound (recursive DNS resolver for privacy & speed), and WireGuard (secure VPN for remote access). For monitoring, tools Uptime Kuma, Netdata, or Prometheus with Grafana provide real-time insights into network performance and security.
MentorPi is a robot car platform powered by the Raspberry Pi 5 and compatible with ROS2, offering options for Mecanum or Ackermann chassis. It includes features like obstacle avoidance, line tracking, and SLAM capabilities, making it suitable for robotics education and development.
Review of the Pironman 5 Max, a Raspberry Pi 5 tower PC enclosure featuring dual M.2 PCI sockets for SSDs or AI accelerators, with detailed assembly, performance, and cooling tests.
This guide shows how to work around low performance issues when running Ubuntu 24.04 on a Raspberry Pi 5 by adjusting the EEPROM config file to override the maximum current value.
