github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11467] Add hardware requirement filters to make model selection easier #7569

New Issue
Open
opened 2026-04-12 19:39:54 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 19:39:54 -05:00
Owner
Copy Link

Originally created by @zongmi on GitHub (Jul 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11467

Currently it's hard to know if a model will work on my hardware:

CPU-only support?

How much RAM needed?

GPU compatibility?

Experienced users can check specs, but beginners often download wrong models. Would be great to have:
Traffic-light compatibility labels (like HF)
Clear minimum requirements
Filter by hardware

This would save noobs like me from failed downloads. Thanks!

Originally created by @zongmi on GitHub (Jul 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11467 Currently it's hard to know if a model will work on my hardware: CPU-only support? How much RAM needed? GPU compatibility? Experienced users can check specs, but beginners often download wrong models. Would be great to have: Traffic-light compatibility labels (like HF) Clear minimum requirements Filter by hardware This would save noobs like me from failed downloads. Thanks!
GiteaMirror added the feature request label 2026-04-12 19:39:54 -05:00
GiteaMirror commented 2026-04-12 19:39:55 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 18, 2025):

The fundamental number you need to be aware of is the size of the model shown on the model card. This is the minimum amount of memory you will need to load the model, whether VRAM or system RAM. If you want to process large prompts, then you will need more memory.

There is no requirement for a GPU, ollama will work fine in a CPU only system. A GPU will make a model run faster, though.

GPU compatibility is shown here. Nvidia has a little better coverage but in general, if the GPU is recent it's likely supported.

<!-- gh-comment-id:3089305825 --> @rick-github commented on GitHub (Jul 18, 2025): The fundamental number you need to be aware of is the size of the model shown on the model card. This is the minimum amount of memory you will need to load the model, whether VRAM or system RAM. If you want to process large prompts, then you will need more memory. There is no requirement for a GPU, ollama will work fine in a CPU only system. A GPU will make a model run faster, though. GPU compatibility is shown [here](https://github.com/ollama/ollama/blob/main/docs/gpu.md#gpu). Nvidia has a little better coverage but in general, if the GPU is recent it's likely supported.
GiteaMirror commented 2026-04-12 19:39:55 -05:00
Author
Owner
Copy Link

@zongmi commented on GitHub (Jul 21, 2025):

Apologies, my previous description was inaccurate. I was referring to my experience as a first-time beginner.
I am proficient in using it now. However, when I was browsing Hugging Face, it made me think about the model search and browsing on Ollama, and I was reminded of the time I spent when I first started with it and was trying to find suitable models. I like Ollama, and I would be very happy if more people could use it. Therefore, I am proposing this suggestion to make it more friendly for absolute beginners, in the hope that Ollama can attract a larger user base.

<!-- gh-comment-id:3095729091 --> @zongmi commented on GitHub (Jul 21, 2025): Apologies, my previous description was inaccurate. I was referring to my experience as a first-time beginner. I am proficient in using it now. However, when I was browsing Hugging Face, it made me think about the model search and browsing on Ollama, and I was reminded of the time I spent when I first started with it and was trying to find suitable models. I like Ollama, and I would be very happy if more people could use it. Therefore, I am proposing this suggestion to make it more friendly for absolute beginners, in the hope that Ollama can attract a larger user base.
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 feature request
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#7569
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?