Geekzone: technology news, blogs, forums
Guest
Welcome Guest.
You haven't logged in yet. If you don't have an account you can register now.


Batman

Mad Scientist
29717 posts

Uber Geek

Trusted
Lifetime subscriber

#318570 30-Jan-2025 20:27
Send private message

trying to install Docker to run OpenWebUI on a Ryzen 5500 with GTX 1070. Not sure why WSL won't install.

 

is it that my PC specs is too low? or something else?

 

thanks


Create new topic
freitasm
BDFL - Memuneh
79140 posts

Uber Geek

Administrator
ID Verified
Trusted
Geekzone
Lifetime subscriber

  #3337541 30-Jan-2025 21:10
Send private message

What Windows version, how much memory?





Please support Geekzone by subscribing, or using one of our referral links: Samsung | AliExpress | Wise | Sharesies | Hatch | GoodSyncBackblaze backup




Batman

Mad Scientist
29717 posts

Uber Geek

Trusted
Lifetime subscriber

  #3337552 30-Jan-2025 22:31
Send private message

Windows 11 Pro, 16GB


networkn
Networkn
32243 posts

Uber Geek

ID Verified
Trusted
Lifetime subscriber

  #3337587 31-Jan-2025 08:27
Send private message

How about an error message? 




gehenna
8460 posts

Uber Geek

Moderator
Trusted
Lifetime subscriber

  #3337626 31-Jan-2025 10:21
Send private message

This is an impossible thread to contribute to until you provide comprehensive information about your environment, errors, general setup and anything that you've changed/modified recently that may have caused problems afterwards.  Can you post a useful summary please?


networkn
Networkn
32243 posts

Uber Geek

ID Verified
Trusted
Lifetime subscriber

  #3337627 31-Jan-2025 10:26
Send private message

gehenna:

 

This is an impossible thread to contribute to until you provide comprehensive information about your environment, errors, general setup and anything that you've changed/modified recently that may have caused problems afterwards.  Can you post a useful summary please?

 

 

You said it far more gracefully than I. 

 

 


TwoSeven
1615 posts

Uber Geek

Subscriber

  #3337931 31-Jan-2025 22:29
Send private message

Windows 11 pro will be fine, so long as it is 22H2 or later (I use 24H2).

 

 

 

 

 

 

 

 

 

 





Software Engineer
   (the practice of real science, engineering and management)

 

Gender Neutral
   (a person who believes in equality and who does not believe in/use stereotypes. Examples such as gender, binary, nonbinary, male/female etc.)

 

 ...they/their/them...


michaelmurfy
meow
13217 posts

Uber Geek

Moderator
ID Verified
Trusted
Lifetime subscriber

  #3337945 1-Feb-2025 02:59
Send private message

Batman: Windows 11 Pro, 16GB

 

After playing around with running a bunch of AI models I think you're going to struggle getting anything really running with 16gb of ram. These are incredibly memory hungry. You should chuck in an extra 16gb.

 

Have a play around with LM Studio instead: https://lmstudio.ai/ - it's more user friendly and can run everything including DeepSeek and Llama totally fine. The more ram the better along with having a dedicated GPU.

 

I was experimenting around tonight (crap where did that time go) with a few models running on a server with 32 CPU cores and assigned 16gb of ram and even then AI models do run slow on CPU alone however you chuck in a decent GPU (the GTX 1070 may work, but could be a little too old) and performance improves greatly.





Michael Murphy | https://murfy.nz
Referral Links: Quic Broadband (use R122101E7CV7Q for free setup)

Are you happy with what you get from Geekzone? Please consider supporting us by subscribing.
Opinions are my own and not the views of my employer.


 
 
 
 

Shop now on Samsung phones, tablets, TVs and more (affiliate link).
Batman

Mad Scientist
29717 posts

Uber Geek

Trusted
Lifetime subscriber

  #3338014 1-Feb-2025 12:15
Send private message

michaelmurfy:

 

Batman: Windows 11 Pro, 16GB

 

After playing around with running a bunch of AI models I think you're going to struggle getting anything really running with 16gb of ram. These are incredibly memory hungry. You should chuck in an extra 16gb.

 

Have a play around with LM Studio instead: https://lmstudio.ai/ - it's more user friendly and can run everything including DeepSeek and Llama totally fine. The more ram the better along with having a dedicated GPU.

 

I was experimenting around tonight (crap where did that time go) with a few models running on a server with 32 CPU cores and assigned 16gb of ram and even then AI models do run slow on CPU alone however you chuck in a decent GPU (the GTX 1070 may work, but could be a little too old) and performance improves greatly.

 

 

thanks, lmstudio is amazing, just one click and everything is installed

 

interestingly, 13900k + 4090 vs MBPro vs 5500 + 1070 is roughly the same speed for deepseek in gwen aka rather slow.

 

llama is a lot faster, not sure if that means anything.

 

have deleted docker as i don't want windows virtual Machine turned on (apparently makes games slower?)


Batman

Mad Scientist
29717 posts

Uber Geek

Trusted
Lifetime subscriber

  #3338015 1-Feb-2025 12:16
Send private message

gehenna:

 

This is an impossible thread to contribute to until you provide comprehensive information about your environment, errors, general setup and anything that you've changed/modified recently that may have caused problems afterwards.  Can you post a useful summary please?

 

 

well it didn't have that when it said failed. after some digging around it says i need to turn on virtual machine.

 

i've deleted docker and now running LM Studio


Create new topic





News and reviews »

Māori Artists Launch Design Collection with Cricut ahead of Matariki Day
Posted 15-Jun-2025 11:19


LG Launches Upgraded webOS Hub With Advanced AI
Posted 15-Jun-2025 11:13


One NZ Satellite IoT goes live for customers
Posted 15-Jun-2025 11:10


Bolt Launches in New Zealand
Posted 11-Jun-2025 00:00


Suunto Run Review
Posted 10-Jun-2025 10:44


Freeview Satellite TV Brings HD Viewing to More New Zealanders
Posted 5-Jun-2025 11:50


HP OmniBook Ultra Flip 14-inch Review
Posted 3-Jun-2025 14:40


Flip Phones Are Back as HMD Reimagines an Iconic Style
Posted 30-May-2025 17:06


Hundreds of School Students Receive Laptops Through Spark Partnership With Quadrent's Green Lease
Posted 30-May-2025 16:57


AI Report Reveals Trust Is Key to Unlocking Its Potential in Aotearoa
Posted 30-May-2025 16:55


Galaxy Tab S10 FE Series Brings Intelligent Experiences to the Forefront with Premium, Versatile Design
Posted 30-May-2025 16:14


New OPPO Watch X2 Launches in New Zealand
Posted 29-May-2025 16:08


Synology Premiers a New Lineup of Advanced Data Management Solutions
Posted 29-May-2025 16:04


Dyson Launches Its Slimmest Vaccum Cleaner PencilVac
Posted 29-May-2025 15:50


OPPO Reno13 Pro 5G Review
Posted 29-May-2025 15:33









Geekzone Live »

Try automatic live updates from Geekzone directly in your browser, without refreshing the page, with Geekzone Live now.



Are you subscribed to our RSS feed? You can download the latest headlines and summaries from our stories directly to your computer or smartphone by using a feed reader.