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 #4975] Is RTX 4070 and not RTX 4070ti supported - ambigous documentation #28904

New Issue
Closed
opened 2026-04-22 07:27:20 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 07:27:20 -05:00
Owner
Copy Link

Originally created by @thinkrapido on GitHub (Jun 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4975

What is the issue?

Hello,

my prompts to ollama model codellama:34b-code-q6_K is taking very long to process.
And in the CPU Monitor many CPUs get envolved when calculating an answer.
What am I doing wrong? Is it a bug or do I have to bear with it?
I expect answers within a second delay.

The documentation at NVIDIA (https://www.nvidia.com/de-de/geforce/graphics-cards/40-series/rtx-4070-family/) says that it is CUDA-Enabled, but on https://github.com/ollama/ollama/blob/main/docs/gpu.md it is not listed for capability 8.9.

I'm using a linux system with the latest CUDA Libraries enabled.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

ollama version is 0.1.24

Originally created by @thinkrapido on GitHub (Jun 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4975 ### What is the issue? Hello, my prompts to ollama model codellama:34b-code-q6_K is taking very long to process. And in the CPU Monitor many CPUs get envolved when calculating an answer. What am I doing wrong? Is it a bug or do I have to bear with it? I expect answers within a second delay. The documentation at NVIDIA (https://www.nvidia.com/de-de/geforce/graphics-cards/40-series/rtx-4070-family/) says that it is CUDA-Enabled, but on https://github.com/ollama/ollama/blob/main/docs/gpu.md it is not listed for capability 8.9. I'm using a linux system with the latest CUDA Libraries enabled. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version ollama version is 0.1.24
GiteaMirror added the bug label 2026-04-22 07:27:20 -05:00
GiteaMirror commented 2026-04-22 07:27:22 -05:00
Author
Owner
Copy Link

@d-kleine commented on GitHub (Jun 12, 2024):

I am using an RTX 3080 Ti and this is not in the list too, but CUDA works with ollama for me. I think the ollama's GPU documentation is just outdated (for Ollama, only the part about the Compute Capability is relevant). So not a Ollama issue most likely.

Did you install cuDNN on your system? Which versions are you using?

  • Nvidia graphics drivers
  • CUDA
  • cuDNN

Try to update to the newest Nvidia graphics driver, CUDA, cuDNN, I just did that yesterday and works perfectly fine for me.

<!-- gh-comment-id:2163695739 --> @d-kleine commented on GitHub (Jun 12, 2024): I am using an RTX 3080 Ti and this is not in the list too, but CUDA works with ollama for me. I think the ollama's GPU documentation is just outdated (for Ollama, only the part about the Compute Capability is relevant). So not a Ollama issue most likely. Did you install cuDNN on your system? Which versions are you using? - Nvidia graphics drivers - CUDA - cuDNN Try to update to the newest Nvidia graphics driver, CUDA, cuDNN, I just did that yesterday and works perfectly fine for me.
GiteaMirror commented 2026-04-22 07:27:23 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jun 14, 2024):

Both are supported. I've updated the docs w/ #5036 . @thinkrapido the problem is you're loading a model which is too big for your GPU. You can use ollama ps to see what percentage of the model is being loaded onto CPU vs GPU.

<!-- gh-comment-id:2166983801 --> @pdevine commented on GitHub (Jun 14, 2024): Both are supported. I've updated the docs w/ #5036 . @thinkrapido the problem is you're loading a model which is too big for your GPU. You can use `ollama ps` to see what percentage of the model is being loaded onto CPU vs GPU.
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 bug
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#28904
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?