Nope. From 5 GB for llama-3 8B to 40GB for llama-3 70B. Check it out here at @ollama
:
HARDWARE
-
Llama-3 Memory Requirements: 5GB to 40GB Across Model Sizes
By
–
-
Excellent Build Quality and User Interaction Experience
By
–
The build quality on this is so good! Really nice to interact with
-
Dusty Secures Major 7-Figure Enterprise Contract for Warehouse Robots
By
–
Convinced that Dusty would be an integral part of all their upcoming warehouse build-outs, they inked a 7-figure enterprise contract for multiple robots deployed over the next three years. This is how we win.
-
Unexpected opportunity leads to warehouse automation pilot contract
By
–
I almost didn't take the call. Robotic warehouse automation was not in our ICP. Luckily my team overrode me and took the meeting. The automation company was intrigued, and we agreed to an annual contract with a pilot period to try a FieldPrinter on their next build-out.
-
Building GPU-Accelerated Generative AI on Azure
By
–
How are you building #generativeAI applications? Deliver a presentation at #MSBuild on your GPU-accelerated solution that leverages NVIDIA AI software on Microsoft @Azure
. Submit here: https://
nvda.ws/3Un4S3A -
UAI’s At-Memory Compute Architecture Leads AI Inference Market
By
–
"UAI's approach to designing inference accelerators means real-world relevance today – not sometime in the future." Read @MoorInsStrat
's latest research brief on the #AI inference market and how our at-memory compute architecture is leading the charge. https://
tinyurl.com/44cy5cxp -
Buffett’s Apple Strategy and ON Semi’s Semiconductor Turnaround
By
–
Sell-side most interesting: Be like Buffett on Apple, ON Semi’s turnaround Warren Buffett knows how to handle Apple shares, by buying the dips, ON Semiconductor offers a weak report that nevertheless provides hope, and there’s a short list of potential buyers for silicon carbide
-
Tech Giants’ AI Spending Surge Drives Nvidia Stock Rally
By
–
The TL Podcast for April 29th: Redeemed by cloud spending Nvidia surged on Friday after Microsoft and Alphabet joined Meta in reiterating their commitment to spend, spend, spend on artificial intelligence, Tesla got a pass on tough questions, and Lam Research and Texas
-
Groq CEO discusses fast token generation and AI expansion plans
By
–
Chatting with @GroqInc
’s CEO @JonathanRoss321
. Groq has super fast token generation capabilities now. And, I was excited also to hear about his plans to scale up capacity aggressively and also expand this to other models than just LLMs! This is a good time to be building AI