github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1033] Are these system specs good enough for any models? #62540

New Issue
Closed
opened 2026-05-03 09:30:00 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-05-03 09:30:00 -05:00
Owner
Copy Link

Originally created by @simoovara on GitHub (Nov 7, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1033

Just a question, I have an old laptop that i turned into a server with Ubuntu LTS. It has an AMD E1-6015 APU and 8gb of ram. I would like to know if that's enough to run any of these models, thank you!

Originally created by @simoovara on GitHub (Nov 7, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1033 Just a question, I have an old laptop that i turned into a server with Ubuntu LTS. It has an AMD E1-6015 APU and 8gb of ram. I would like to know if that's enough to run any of these models, thank you!
GiteaMirror commented 2026-05-03 09:30:04 -05:00
Author
Owner
Copy Link

@SebastianMpl commented on GitHub (Nov 7, 2023):

Not for any. Try those <= 7b parameters and q4 or lower (but it also lowers quality). I have 6 gb ram and have about 3 tokens per second with 7b q4km. The speed is like an answer from a real person, not those flashing words...

<!-- gh-comment-id:1799284091 --> @SebastianMpl commented on GitHub (Nov 7, 2023): Not for any. Try those <= 7b parameters and q4 or lower (but it also lowers quality). I have 6 gb ram and have about 3 tokens per second with 7b q4km. The speed is like an answer from a real person, not those flashing words...
GiteaMirror commented 2026-05-03 09:30:05 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Nov 7, 2023):

I don't know much about that AMD processor series so I cant really say for sure, but if you'd like to try the most lightweight model to see what you're system is capable I'd suggest giving orca-mini a try to see if it works: ollama run orca-mini

<!-- gh-comment-id:1799337109 --> @BruceMacD commented on GitHub (Nov 7, 2023): I don't know much about that AMD processor series so I cant really say for sure, but if you'd like to try the most lightweight model to see what you're system is capable I'd suggest giving orca-mini a try to see if it works: `ollama run orca-mini`
GiteaMirror commented 2026-05-03 09:30:06 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Nov 7, 2023):

That's a laptop chip from 2015. It may not be able to run any models at all if it lacks the needed vector instructions. If it can run models on the CPU, it'll be slow, but enough to get a taste.

<!-- gh-comment-id:1799745466 --> @easp commented on GitHub (Nov 7, 2023): That's a laptop chip from 2015. It may not be able to run any models at all if it lacks the needed vector instructions. If it can run models on the CPU, it'll be slow, but enough to get a taste.
GiteaMirror commented 2026-05-03 09:30:07 -05:00
Author
Owner
Copy Link

@simoovara commented on GitHub (Nov 7, 2023):

Alright, really helpful. Will try the lightest model orca-mini and I'll comment on this to let you know how it goes.

<!-- gh-comment-id:1800148513 --> @simoovara commented on GitHub (Nov 7, 2023): Alright, really helpful. Will try the lightest model orca-mini and I'll comment on this to let you know how it goes.
GiteaMirror commented 2026-05-03 09:30:09 -05:00
Author
Owner
Copy Link

@simoovara commented on GitHub (Nov 7, 2023):

Yeah, it's really really slow. It loads for about a minute and then types it out really slowly, approximately 1 word every second.
worth a try though

<!-- gh-comment-id:1800189729 --> @simoovara commented on GitHub (Nov 7, 2023): Yeah, it's really really slow. It loads for about a minute and then types it out really slowly, approximately 1 word every second. worth a try though
GiteaMirror commented 2026-05-03 09:30:10 -05:00
Author
Owner
Copy Link

@simoovara commented on GitHub (Nov 7, 2023):

thanks everyone for the help!

<!-- gh-comment-id:1800190622 --> @simoovara commented on GitHub (Nov 7, 2023): thanks everyone for the help!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#62540
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?