A 110 billion parameter AI model running on a laptop that even a 5090 can’t handle.
PLAUD NotePin ($10 OFF with the code "Alex15"): https://bit.ly/4dCpluf
PLAUD AMAZON: https://amzn.to/4mzJt4f

🛒 Gear Links 🛒
* 🍏💥 New MacBook Air M1 Deal: https://amzn.to/3S59ID8
* 💻🔄 Refurb MacBook Air M1 Deal: https://amzn.to/45K1Gmk
* 🎧⚡ Great 40Gbps T4 enclosure: https://amzn.to/3JNwBGW
* 🛠️🚀 My nvme ssd: https://amzn.to/3YLEySo
* 📦🎮 My gear: https://www.amazon.com/shop/alexziskind

🎥 Related Videos 🎥
* 👨‍💻 Full Z13 review - https://youtu.be/fGEqxHurxZM
* 🌗 How long can they last? | ULTIMATE BATTERY TEST - https://youtu.be/u1XJAOf_W5w
* 👨‍💻 Set up laptop for Software Development - https://youtu.be/3mCZ3WUcM8s
* 👨‍💻 15" MacBook Air | developer's dream - https://youtu.be/A1IOZUCTOkM
* 🤖 INSANE Machine Learning on Neural Engine - https://youtu.be/Y2FOUg_jo7k

* 🛠️ Developer productivity Playlist - https://www.youtube.com/playlist?list=PLPwbI_iIX3aQCRdFGM7j4TY_7STfv2aXX

The device in the vid is Asus Flow Z13 (2025 version)
LLM Memory calculator: https://llm-inference-calculator-rki02.kinsta.page/
Result charts for this vid: https://aziskyt.github.io/https-www.youtube.com-watch-v-AcTmeGpzhBk/

— — — — — — — — —

❤️ SUBSCRIBE TO MY YOUTUBE CHANNEL 📺

Click here to subscribe: https://www.youtube.com/@AZisk?sub_confirmation=1

Join this channel to get access to perks:
https://www.youtube.com/channel/UCajiMK_CY9icRhLepS8_3ug/join

— — — — — — — — —

📱LET'S CONNECT ON SOCIAL MEDIA

ALEX ON TWITTER: https://twitter.com/digitalix

— — — — — — — — —

⏱️ Chapters
00:00 – Huge LLMs on a Laptop
00:50 – Flow Z13 Overview
02:10 – Why 128GB RAM?
04:00 – LLM Tools & Setup
07:30 – Manual vs Auto Memory
10:45 – AMD vs Apple Memory
16:20 – 32GB vs 128GB


#zenbook #flowz13 #laptop  #PLAUD #gadgets #ai

YouTube

The Asus Flow Z13 2025 with AMD's Ryzen AI Max Plus 395 APU can run 110 billion parameter LLMs thanks to its 128GB of unified memory, outperforming many desktop setups. The APU combines CPU and GPU on a single chip, allowing the GPU to access large amounts of shared memory. However, unlike Apple's true unified memory architecture, AMD's implementation requires pre-allocating memory between CPU and GPU at boot time. Performance testing shows that manual memory allocation settings significantly outperform auto settings, with 16GB GPU allocation often providing optimal results. The system's 235 GB/s memory bandwidth enables competitive performance against Apple Silicon, though the memory copying process during model loading reveals architectural limitations compared to true unified memory systems.

This Laptop Runs LLMs Better Than Most Desktops