pruster

llmfit. Useful tool that probes hardware and tells you exactly which LLMs will actually run. - handles MoE expert offloading, picks the best quantization for your RAM, estimates tokens/sec before you even pull the weights. Essential for local dev. github.com/AlexsJones/llm…

@TDataScience @gurezende Love this breakdown. Any chance you’d consider doing a B2B SaaS version next, with account‑level churn?🙏🏻

How to detect silent customer churn using linear regression, step-by-step. By @gurezende towardsdatascience.com/from-transacti…

@itsafiz @ollama whats your hardware setup here?

@ollama Step 3: Download the model of your choice. Make sure that you have enough hardware to support the model that you are downloading. However, Following models are recommended for this use case.

This is huge: Now you can run Claude Code for FREE! It's Sunday, and I tried running Claude Code locally using @ollama. No API costs, no rate limits, 100% local. A step-by-step guide 🧵 👇

App Lab just got a major upgrade! 🚀 You can now export your UNO Q apps, share them, and import projects from the community. This release also features an integrated flasher tool to keep your firmware up to date. Full details here: blog.arduino.cc/2026/02/04/int…

Motor condition monitoring is crucial in industrial settings. José Bagur's application note details how to construct an anomaly detection system utilizing the new Arduino Nesso N1 with its built-in IMU and an @EdgeImpulse AI model: docs.arduino.cc/tutorials/ness…

@Reeeee0758 @eyeonaxis It can be yours for the low low price of some steel wool, and some fine grit polishing compound!

@eyeonaxis That Mosin is a vibe ngl

A Tibetan father and son on a pilgrimage around China's Mount Kailas | Lynn Johnson

Uncle June and Nas (2002) 📸 Jonathan Mannion

🔥🔥 // The tinyML Foundation Undergoes an Evolution: Meet the EDGE AI FOUNDATION - ⁦@Hacksterio⁩ ⁦@TinymlF⁩ hackster.io/news/the-tinym…

The tinyML Foundation has evolved into the EDGE AI FOUNDATION, taking the next leap to support innovation and collaboration in AI at the edge. As a proud contributor and sponsor, Arduino is thrilled to witness the growth of this unique ecosystem. linkedin.com/pulse/from-tin…

The Edge AI Technology Report: Generative AI Edition has been published. The new report, drawing from discussions with industry leaders and technologists, explores how generative AI is being harnessed and integrated into edge environments and what this means for the future of technology. Get it for free here: wevlv.co/gen-edge-ai-so… #edgecomputing #cloudcomputing #edgeai #generativeai #generativeedgeai #engineering #technology #llms #edgegenaireport

Busy, cold night at Stonehenge as we move the stones backwards an hour...

@chris_j_paxton @physical_int Fitted Sheet. Fitted Sheet.

Easily the most impressive uncut autonomous video I've ever seen, from @physical_int

yikes. 😬

Join our webinar on October 23rd as @NordicTweets digs into how Smart Ag applies technologies and solutions to more efficient methods of growing and distributing food, optimizing yields, and minimizing the resources needed to feed our population. // 🌾 events.hackster.io/impactspotligh…

New project: Edge Impulse's AI platform powers a low-cost, automated pick-and-place system, using an @Arduino Braccio ++ robotic arm, @Luxonis OAK-D depth camera, and @Raspberry_Pi 5. Read the post here: edgeimpulse.com/blog/building-…

Meet our new ROI Calculator — live now! Assess the cost of going DIY vs using Edge Impulse for your edge AI solutions. Learn more about the calculator in our announcement post: edgeimpulse.com/blog/introduci… Jump straight into the calculator here: edgeimpulse.com/roi-calculator

#EdgeAI 🤖 Check out this exciting tutorial by Sachin Soni from @IMtechiesms! how to build a voice-controlled LED using our XIAO ESP32S3 Sense board and @EdgeImpulse. 🔊 Capture audio, train a model, and control an LED with voice commands like "Yes" & "No." Watch the full video below. 👇 youtube.com/watch?v=0X0vkz… #ESP32 #ML #techiesms #EdgeImpulse #XIAO #MachineLearning #IoT

We're at @embedded_world North America with @EdgeImpulse, showcasing NVIDIA TAO models deployed on our Ensemble microcontrollers. Stop by and say hello! 👋

Join our webinar “Synthetic Data for the Edge: Speed Up ML Development with @NVIDIA Omniverse and Edge Impulse” and learn how to use synthetic data to get to market faster and increase ML model performance. May 14th, 8am PT/11am ET. Register here: hubs.ly/Q02tmK130

@mjrovai used 14 years of historical weather data to train a model to predict its future #temperature. The trained LSTM (Long Short-Term Memory) model was converted with @TensorFlow Lite to be deployed to #SeeedXIAO ESP32S3 using the @EdgeImpulse Python SDK. bit.ly/3J7edHo