Sumanth P’s Post

View profile for Sumanth P

Machine Learning Developer Advocate | LLMs, AI Agents & RAG | Shipping Open Source AI Apps | X (65K+)

Microsoft just changed the game! 🔥 They've open-sourced bitnet.cpp: a blazing-fast 1-bit LLM inference framework that runs directly on CPUs. You can now run 100B parameter models on local x86 CPU devices with up to 6x speed improvements and 82% less energy consumption. They also released BitNet b1.58 2B4T, the first functional open-source model that uses just 1.58 bits for weights instead of the usual 16 or 32 bits. BitNet b1.58 uses ternary weights (-1, 0, +1) and 8-bit activations, reducing memory needs by ~6x compared to similar-sized models while matching their performance on benchmarks Link to the paper and the repo in the comments! If you're interested in ML, LLMs, RAG, and AI Agents and want to receive Apps and tutorials every week, subscribe to AI Engineering (for free): https://lnkd.in/d9REmcqK

That's interesting. Can we already load it with Ollama?

Like
Reply

Thanks for sharing, Sumanth, that's pretty fast

Vincent Claes

Freelance MLOps / LLMOps Engineer | AI Solutions Architect

6d

The concept is nice, but i heared (not tested myself) that the performance degrades so much that it’s almost unusable. If there is anyone who had a positive experience? I would love to know more!

Ayushman Pranav

MLops Lead @StuvalleyTechnology | GenAi researcher | Devops | 3D responsive Webdev | Forging and Deploying cutting edge Ai Solutions , Follow for Tech advancements

6d
Adedoyin Adeyemi

Sr. ML Engineer | MLOps(Azure) | Data Scientist | BI Analyst | Full-stack Software Developer | AI Engineer | Lecturer | Educator

6d

Thanks for sharing, Sumanth

Paolo Perrone

No BS AI/ML Content | ML Engineer with a Plot Twist 🥷

6d

Ternary weights? 🤯 My brain is still processing this. Huge for the future of AI. Thanks for the link 🔥

Markus Odenthal

8+ years Data Scientist | Exploring & applying practical AI agents to boost Data Professional productivity | Advocate for simple workflows, efficiency, and hype-free AI implementation.

6d

Nice share. Open source small LLM are the future. Just this week I experiment a lot with different models with Ollama.

Shivani Virdi

Engineering at Microsoft | Simplifying AI for Everyone | Empowering Productivity with Proven Frameworks and Processes

6d

Large models getting smaller and I’m here for it, definitely checking this out!

Shashwat Singh

Building @Horizon || TED-Ed Speaker || I also teach Flutter📱 || Taught 10,000+ hour's on Udemy || Creator of 50+ Apps 📱 || Published 3 apps on Play Store || Let's Learn Together! 🌟

6d

Can this be considered a replacement for ollama?........is there a way to run models provided by ollama, using this?

Like
Reply
See more comments

To view or add a comment, sign in

Explore topics