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 #9774] Estimate of VRAM needs based on context length and quantization #52903

New Issue
Open
opened 2026-04-29 01:19:31 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 01:19:31 -05:00
Owner
Copy Link

Originally created by @mmb78 on GitHub (Mar 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9774

It would really help to know what is the VRAM necessary to load and run the models that are available on the Ollama.com site. The needs are enormous when larger context window is set with the num_ctx parameter. In addition, this also depends on quantization of the model. Just a few examples of VRAM needs would be helpful. For example, 2k tokens, 8k, 32k, 128k.
Thank you!

Originally created by @mmb78 on GitHub (Mar 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9774 It would really help to know what is the VRAM necessary to load and run the models that are available on the Ollama.com site. The needs are enormous when larger context window is set with the num_ctx parameter. In addition, this also depends on quantization of the model. Just a few examples of VRAM needs would be helpful. For example, 2k tokens, 8k, 32k, 128k. Thank you!
GiteaMirror added the ollama.comfeature request labels 2026-04-29 01:19:32 -05:00
GiteaMirror commented 2026-04-29 01:19:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 14, 2025):

I did this for a few models a while back here.

<!-- gh-comment-id:2725984416 --> @rick-github commented on GitHub (Mar 14, 2025): I did this for a few models a while back [here](https://github.com/ollama/ollama/issues/6852#issuecomment-2440229918).
GiteaMirror commented 2026-04-29 01:19:35 -05:00
Author
Owner
Copy Link

@RustoMCSpit commented on GitHub (May 10, 2025):

I did this for a few models a while back here.

are these displayed on the website?

<!-- gh-comment-id:2869214755 --> @RustoMCSpit commented on GitHub (May 10, 2025): > I did this for a few models a while back [here](https://github.com/ollama/ollama/issues/6852#issuecomment-2440229918). are these displayed on the website?
GiteaMirror commented 2026-04-29 01:19:37 -05:00
Author
Owner
Copy Link

@RustoMCSpit commented on GitHub (May 10, 2025):

i imagine the best way to go about this is to simply auto-run each uploaded model on gpus from weakest to strongest until one works. youd need to have access to such gpus but after that this becomes a fully automated process.

<!-- gh-comment-id:2869215153 --> @RustoMCSpit commented on GitHub (May 10, 2025): i imagine the best way to go about this is to simply auto-run each uploaded model on gpus from weakest to strongest until one works. youd need to have access to such gpus but after that this becomes a fully automated process.
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 ollama.com
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#52903
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?