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 #10402] Official RTX 5090 Support #68892

New Issue
Closed
opened 2026-05-04 15:35:22 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 15:35:22 -05:00
Owner
Copy Link

Originally created by @stanblesk on GitHub (Apr 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10402

Dear developers, I would like to ask when official support for RTX 5090 will appear? We are planning to purchase them to start working with Ollama. For now, the lack of official support scares us a little.
Thank you in advance for your answer!

Originally created by @stanblesk on GitHub (Apr 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10402 Dear developers, I would like to ask when official support for RTX 5090 will appear? We are planning to purchase them to start working with Ollama. For now, the lack of official support scares us a little. Thank you in advance for your answer!
GiteaMirror added the model label 2026-05-04 15:35:22 -05:00
GiteaMirror commented 2026-05-04 15:35:50 -05:00
Author
Owner
Copy Link

@TheArKaID commented on GitHub (Apr 25, 2025):

I'm able to run Ollama within Docker. Or you mentioning other kind of "official support"?

Image

<!-- gh-comment-id:2829853194 --> @TheArKaID commented on GitHub (Apr 25, 2025): I'm able to run Ollama within Docker. Or you mentioning other kind of "official support"? ![Image](https://github.com/user-attachments/assets/6df868e9-4c4d-4128-8ef7-e249e91da42e)
GiteaMirror commented 2026-05-04 15:35:50 -05:00
Author
Owner
Copy Link

@FlippingBinary commented on GitHub (Apr 25, 2025):

Same here. My only pain point so far had nothing to do with Ollama directly, but I'll mention it because it was Ollama-adjacent. I was using Kokoro-FastAPI for text to speech in Open-WebUI to read Ollama's output until I upgraded to the 5090 and discovered Kokoro-FastAPI depends on PyTorch 2.6, which doesn't support Blackwell. However, that shouldn't be a problem much longer because PyTorch 2.7 was just released two days ago with support for Blackwell.

In other words, you really shouldn't have a problem.

<!-- gh-comment-id:2830606428 --> @FlippingBinary commented on GitHub (Apr 25, 2025): Same here. My only pain point so far had nothing to do with Ollama directly, but I'll mention it because it was Ollama-adjacent. I was using Kokoro-FastAPI for text to speech in Open-WebUI to read Ollama's output until I upgraded to the 5090 and discovered Kokoro-FastAPI depends on PyTorch 2.6, which doesn't support Blackwell. However, that shouldn't be a problem much longer because PyTorch 2.7 was just released two days ago with support for Blackwell. In other words, you really shouldn't have a problem.
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 model
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#68892
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?