Like everyone, I've been a bit distracted exploring @deepseek_ai R1 and experimenting with it locally.
I've spoken to a few people recently who don't know how to run local LLMs - this thread will cover a few different tools to get up and running easily.
🥔 Dr Zdenka Kuncic's nanowire networks (hundreds of thousands of self-adjusting memristors) achieve machine intelligence in the hardware itself—no software needed.
"This means that they can self-adjust their weights to changing input signals." 🤯
Microsoft just changed the game! 🔥
They've open-sourced bitnet.cpp: a blazing-fast 1-bit LLM inference framework that runs directly on CPUs.
Why is this a game-changer❓
You can now run 100B parameter models on local devices with up to 6x speed improvements and 82% less energy consumption—all without a GPU!
The future we've been waiting for: fast, efficient, and private AI that works anytime, anywhere.✨
Link to the GitHub repo in next tweet!
_____
Find me → @akshay_pachaar ✔️
For more insights and tutorials on AI and Machine Learning!
The easiest way to use this new model is through HuggingChat with the link below.
Just create a free account and select the model “nvidia/Llama-3.1-Nemotron-70B-Instruct-HF”.
And you're ready to start chatting!
Your free AI writing assistant:
1. Chat with super human
https://t.co/1rGuvyspJr
2. Write blogs, content with AI
https://t.co/kUsHxTIz6x
3. AI spelling, grammar checker
https://t.co/aHZBoc42C0
4. Content creation superpower
https://t.co/FJdhC5aSkI
Tiny urban forests can help #rewild urban settings and help fight #climatechange. The brainchild of the Japanese botanist Miyawaki is taking his idea global.
We have so many solutions. Let's stop the delays and implement them. #ActOnClimate#climate#forests#nature
Amazon Prime days are coming. Designing a system with extremely high concurrency, high availability, and quick responsiveness needs to consider many aspects 𝐚𝐥𝐥 𝐭𝐡𝐞 𝐰𝐚𝐲 𝐟𝐫𝐨𝐦 𝐟𝐫𝐨𝐧𝐭𝐞𝐧𝐝 𝐭𝐨 𝐛𝐚𝐜𝐤𝐞𝐧𝐝.
Love this video on using GitHub Codespaces for embedded development. Makes it so much easier to manage the different dev boxes set up for each board. @github@code@MicrosoftIoT
https://t.co/k6OyShWxWQ