Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

HOW TO RUN AN AI MODEL FROM A USB FLASH DRIVE

94,394 Aufrufe • vor 1 Monat •via X (Twitter)

34 Kommentare

Profilbild von Luís Rodrigues
Luís Rodriguesvor 1 Monat

The real trick isn't the USB. It's having a model small enough to fit in memory and an inference runtime that can run locally.

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

True 😅

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

Keep in mind that while running LLMs off a USB drive works, it’s mostly meant for testing and light everyday tasks. Heavy-duty AI generation will demand a high-end system!

Profilbild von Vínx Corváel
Vínx Corváelvor 1 Monat

Niiiiice

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

Try it out

Profilbild von Vínx Corváel
Vínx Corváelvor 1 Monat

I legit just bought a portable SSD sandisk so I'll be setting this up hopefully this week

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

It's just for testing tho 😂

Profilbild von Vínx Corváel
Vínx Corváelvor 1 Monat

nawwwww I'm doing it... and then telling everyone you told me to 🤣 I needed portable storage anyway btw lol

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

Have fun 😂😂

Profilbild von Rahul
Rahulvor 1 Monat

Why do u need usb flash here?

Profilbild von ABDULAZIZ ALNEMASH
ABDULAZIZ ALNEMASHvor 1 Monat

@TranslateMom arabic

Profilbild von The Universal Heartthrob
The Universal Heartthrobvor 1 Monat

What's the procedure for a Linux usb or what's different in a Linux install

Profilbild von raymonjohns
raymonjohnsvor 1 Monat

Can it work with vscode

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

Yes it can, but it completely depends on the model size. Small quantized models (1B–3B) only need ~2–4 GB of RAM and can run in the background while coding. However, I wouldn't advise relying on local setups unless you have a high-end PC. This video is mostly for testing and running offline experiments, competent coding models need significantly more resources to be practical.

Profilbild von Thangchp
Thangchpvor 1 Monat

not working!

Profilbild von Frank Rojas
Frank Rojasvor 1 Monat

Thanks!

Profilbild von TranslateMom
TranslateMomvor 1 Monat

With Arabic captions:

Profilbild von Grueber
Gruebervor 1 Monat

@SagirGurin

Profilbild von Yand
Yandvor 1 Monat

is the model free?

Profilbild von TheTobeGphx🖋️🇳🇬🇬🇧
TheTobeGphx🖋️🇳🇬🇬🇧vor 1 Monat

@xdownloadercom download this please.

Profilbild von Moet
Moetvor 1 Monat

Hmmm

Profilbild von FATÉ
FATÉvor 1 Monat

So far it's not unsencored it's just a turn off for me

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

???

Profilbild von NorthernLights.XRP
NorthernLights.XRPvor 1 Monat

@lyonjacobsfe ...Flash Drive Modem

Profilbild von Assente Arbitrario
Assente Arbitrariovor 1 Monat

@GBallarani tiè...

Profilbild von offNomansLand
offNomansLandvor 1 Monat

That’s awesome! How can I do this on a Mac OS?

Profilbild von Madhu V
Madhu Vvor 1 Monat

Any good for working with Visual studio or vs code. As direct plugins are very slow

Profilbild von Ø.
Ø.vor 1 Monat

•

Profilbild von nemonik 🇺🇲🐶
nemonik 🇺🇲🐶vor 1 Monat

You can install snd keep up to data ollama and python via the scoop package manager for Windows and the huggingface cli via pip...

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

Scoop is great for managing CLI tools on a primary PC. However, it requires an internet connection to install dependencies, which defeats the point of a portable, plug-and-play USB drive designed to run 100% offline on any PC without prior setup

Profilbild von nemonik 🇺🇲🐶
nemonik 🇺🇲🐶vor 1 Monat

$env:SCOOP_CACHE = "E:\ScoopCache" #drive letter of your usb drive scoop download python ... scoop install python ... mkdir E:\wheels pip download -d E:\wheels hungingface... And Bob's your uncle.

Profilbild von nemonik 🇺🇲🐶
nemonik 🇺🇲🐶vor 1 Monat

That pip part is a bit fussy maybe $env:PIP_CACHE_DIR = "E:\pip-cache" pip config set global.cache-dir "E:\pip-dir "E:\pip-cache Would be better.

Profilbild von Axel
Axelvor 1 Monat

How do I export the conversation to pdf? Can it?

Profilbild von 𝐇𝐚𝐦𝐳𝐚 | Networking Guy
𝐇𝐚𝐦𝐳𝐚 | Networking Guyvor 1 Monat

It's running on your browser so Ctrl+ P and save as pdf

Ähnliche Videos