livellosegreto.it is one of the many independent Mastodon servers you can use to participate in the fediverse.
Livello Segreto è il social etico che ha rispetto di te e del tuo tempo.

Administered by:

Server stats:

1.2K
active users

#edgeai

1 post1 participant0 posts today

📱 Small Language Models (SLMs) are gaining traction! 🧠

These compact AI models run efficiently on local devices while offering impressive capabilities:
- Enhanced privacy (your data stays on your device)
- Lower computational costs
- Minimal latency
- Works offline

Perfect for specific tasks where you don't need the full power of massive models.

Have you tried any SLMs yet?

Can I run an #Apple (M3/M4) machine headless to experiment with local #LLMs?

What I want to achieve:
🎙️ Audio transcription
📝 Automatic summarization + minutes of meeting generation
🌐 Ideally with a local web-based GUI

Requirements:
✅ Full use of Apple Silicon performance (M3/M4)
✅ Headless setup
✅ Support for different open-source LLMs

Are there any existing solutions or projects that match this use case?
Any tips or experiences welcome!

#AppleSilicon #OnDeviceAI #LLM #OpenSource #AI #SelfHosted #EdgeAI #PrivateAI

Shuttle presents the new XPC slim DN11 series - compact AI-PCs powered by Intel Core Ultra. With up to 34 TOPS, quad 2.5 Gbit LAN, support for four 4K displays, and space for three M.2-2280 SSDs, they’re ready for demanding edge applications. Learn more: go.shuttle.eu/DN11

Oh, and by the way: Germany’s @ct_Magazin has already published a hands-on review (paywall): go.shuttle.eu/plBGJ

I just backed this project on Kickstarter: kickstarter.com/projects/openm

OpenMV LLC makes some incredibly powerful, small-form-factor #IoT cameras perfect for tinkering, prototyping, and making slick projects. I taught my Computer Vision with #AI course using their cameras. I'm excited about this new series: full object detection for a few mW. #EdgeAI #ComputerVision #Arduino #MicroPython #embedded #microcontroller

🚀 Edge AI Mini Guide 🚀

Edge AI enables real-time decision-making by processing data locally on devices like IoT sensors & cameras.

Steps:
1️⃣ Identify use cases (e.g., predictive maintenance).
2️⃣ Assess data needs & hardware capabilities.
3️⃣ Develop lightweight AI models.
4️⃣ Build efficient data pipelines.
5️⃣ Monitor & optimize performance.

🔑 Tips: Prioritize scalability + security!

Questions or tips? Reply below! 🧵

🚀 Meet Jolla at CES 2025!
Join us in Las Vegas from January 7-10, 2025, and discover how we're advancing Edge AI for automotive and personal computing!

🌟 What to Expect:
🔹 Live demos showcasing Edge AI in automotive and personal computing
🔹 Expert insights from the Jolla team

📍 Where: Demo suite @ Hilton Grand Vacations on the Strip
Co-located with our partner company, Seafarix

🗓 When: Tuesday–Friday, January 7–10, 2025

Experience the future of AI and privacy from Finland with Jolla Mind2.