De pouvoir le faire tourner sur des tout petit dévices comme le RPI pour des applications embarqué offline par exemple mdr
AI HARDWARE
-
Fashion Content Creation with Segment Anything 2 and Open Source Models
By
–
With a stack leveraging Segment Anything 2, an RTX 4090 and a collection of open source models and utilities, Josephine Miller is creating runway-ready fashion content ➡️ https://t.co/TIXcyRVYyy pic.twitter.com/ek49D1s2K3
— AI at Meta (@AIatMeta) 23 janvier 2025With a stack leveraging Segment Anything 2, an RTX 4090 and a collection of open source models and utilities, Josephine Miller is creating runway-ready fashion content https://
go.fb.me/slwyw5 -
AI Agents Running on Embedded AI Hardware Recursively
By
–
How soon until the little AI computer is running its own little agent, with its own little AI computer
-
AI agents with their own dedicated AI computers
By
–
It's so cute to imagine an AI agent with its own little AI computer.
-
DeepSeek R1 7B: Best On-Device Reasoning Model
By
–
here’s deepseek r1 7b running @ 10 tok/s
— Aaron Ng (@localghost) 23 janvier 2025
best reasoning model you can run on a phone today. might just be what you need if the internet goes out suddenly. pic.twitter.com/rL6daIihFLhere’s deepseek r1 7b running @ 10 tok/s best reasoning model you can run on a phone today. might just be what you need if the internet goes out suddenly.
-
Microsoft’s Stargate Project and Responsible AI Infrastructure Investment
By
–
Et le pire dans ce projet « stargate » ? 😲
— Defend Intelligence (Anis Ayari) (@DFintelligence) 23 janvier 2025
Satya Nadella, le CEO de Microsoft, a déclaré qu’il avait les moyens financiers 💰, mais qu’il veillerait à ce que cet argent soit utilisé de manière responsable ✅, pour des projets sérieux, et non pour simplement surfer sur la hype… pic.twitter.com/oI0f7XEDSAEt le pire dans ce projet « stargate » ? Satya Nadella, le CEO de Microsoft, a déclaré qu’il avait les moyens financiers , mais qu’il veillerait à ce que cet argent soit utilisé de manière responsable , pour des projets sérieux, et non pour simplement surfer sur la hype
-
SambaNova Advances AI Chip Technology at WEF25
By
–
Exciting to see the conversation around #AI & #semiconductors at #WEF25! As @BloombergHT highlights, the demand for powerful & efficient computing hardware is skyrocketing. We're working to address this need with our advanced AI chips. Learn more: https://
sambanova.ai. #Davos -
Tiny 1.5B Model Outperforms GPT-4o, Runs Offline
By
–
“outperforms GPT-4o and Claude-3.5-Sonnet on math benchmarks”
— Aaron Ng (@localghost) 22 janvier 2025
Here it is running on a phone, completely offline.
Tiny 1.5B AI model that will run on almost any hardware, even without internet.
Are you getting it yet? https://t.co/RjXTKvsRPd pic.twitter.com/6GimUSBKOo“outperforms GPT-4o and Claude-3.5-Sonnet on math benchmarks” Here it is running on a phone, completely offline. Tiny 1.5B AI model that will run on almost any hardware, even without internet. Are you getting it yet?
-
Axelera AI Showcases Edge AI Acceleration Technology at HiPEAC
By
–
Great connecting at #HiPEAC2025! 🚀 @HiPEAC helped us share how Axelera AI’s cutting-edge tech accelerates edge #AI projects across industries. Did we see you there? Drop a comment if so! 💡 #EdgeAI #AIAccelerationhttps://t.co/IHDmb2Zmpn pic.twitter.com/5fEarkjh4n
— Axelera AI (@AxeleraAI) 22 janvier 2025Great connecting at #HiPEAC2025! @HiPEAC helped us share how Axelera AI’s cutting-edge tech accelerates edge #AI projects across industries. Did we see you there? Drop a comment if so! #EdgeAI #AIAcceleration https://
axelera.ai