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 #8894] Could not connect to a running Ollama instance (windows 11) #67824

New Issue
Closed
opened 2026-05-04 11:48:09 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-04 11:48:09 -05:00
Owner
Copy Link

Originally created by @ShaneK6079 on GitHub (Feb 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8894

What is the issue?

I downloaded Ollama for windows 11 and it will not connect. Firewalls are down. updated all my nvidia drivers. I added screen shots of all the system specifics.

What do I need to do to resolve this on my system? Or is this a Ollama bug?

Image

Image

Image

Image

Image

app-1.log
app-5.log
server-5.log
server-4.log
server-3.log
server-2.log
server-1.log
server.log
app.log

Relevant log output

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.5.7

Originally created by @ShaneK6079 on GitHub (Feb 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8894 ### What is the issue? I downloaded Ollama for windows 11 and it will not connect. Firewalls are down. updated all my nvidia drivers. I added screen shots of all the system specifics. What do I need to do to resolve this on my system? Or is this a Ollama bug? ![Image](https://github.com/user-attachments/assets/ff7efbe9-9614-4f90-ae94-3755feae1b64) ![Image](https://github.com/user-attachments/assets/fbdb128f-4d39-4e9a-96ea-fce286441397) ![Image](https://github.com/user-attachments/assets/15158cab-58fe-4531-b56d-0f31203b95a0) ![Image](https://github.com/user-attachments/assets/b935fa6d-a7b1-4b5d-a54c-316774f89b73) ![Image](https://github.com/user-attachments/assets/e9a65fb5-b948-4018-a523-3693390e21e9) [app-1.log](https://github.com/user-attachments/files/18694825/app-1.log) [app-5.log](https://github.com/user-attachments/files/18694822/app-5.log) [server-5.log](https://github.com/user-attachments/files/18694823/server-5.log) [server-4.log](https://github.com/user-attachments/files/18694824/server-4.log) [server-3.log](https://github.com/user-attachments/files/18694828/server-3.log) [server-2.log](https://github.com/user-attachments/files/18694827/server-2.log) [server-1.log](https://github.com/user-attachments/files/18694829/server-1.log) [server.log](https://github.com/user-attachments/files/18694826/server.log) [app.log](https://github.com/user-attachments/files/18694821/app.log) ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.5.7
GiteaMirror added the bugwindowsnvidiagpu labels 2026-05-04 11:48:11 -05:00
GiteaMirror commented 2026-05-04 11:48:16 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 6, 2025):

nvmlInit_v2 err: 999
time=2025-02-06T11:53:28.697-07:00 level=INFO source=gpu.go:654 msg="Unable to load NVML management library C:\\WINDOWS\\system32\\nvml.dll: nvml vram init failure: 999"
nvmlInit_v2 err: 999
time=2025-02-06T11:53:28.700-07:00 level=INFO source=gpu.go:654 msg="Unable to load NVML management library c:\\Windows\\System32\\nvml.dll: nvml vram init failure: 999"

time=2025-02-06T11:53:28.710-07:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths="[C:\\Users\\emso\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cudart64_110.dll C:\\Users\\emso\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cudart64_12.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.8\\bin\\cudart64_12.dll c:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.8\\bin\\cudart64_12.dll]"
Exception 0xc0000005 0x0 0x3d18 0x7ffc1958f5ca
PC=0x7ffc1958f5ca
signal arrived during external code execution

runtime.cgocall(0x7ff6496b0720, 0xc000520c08)
	runtime/cgocall.go:167 +0x3e fp=0xc000520be0 sp=0xc000520b78 pc=0x7ff6488f9c3e
github.com/ollama/ollama/discover._Cfunc_cudart_init(0x280a83e60e0, 0xc0000fe300)

Server crashed during initialization. What's the output of nvidia-smi?

<!-- gh-comment-id:2640753762 --> @rick-github commented on GitHub (Feb 6, 2025): ``` nvmlInit_v2 err: 999 time=2025-02-06T11:53:28.697-07:00 level=INFO source=gpu.go:654 msg="Unable to load NVML management library C:\\WINDOWS\\system32\\nvml.dll: nvml vram init failure: 999" nvmlInit_v2 err: 999 time=2025-02-06T11:53:28.700-07:00 level=INFO source=gpu.go:654 msg="Unable to load NVML management library c:\\Windows\\System32\\nvml.dll: nvml vram init failure: 999" time=2025-02-06T11:53:28.710-07:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths="[C:\\Users\\emso\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cudart64_110.dll C:\\Users\\emso\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cudart64_12.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.8\\bin\\cudart64_12.dll c:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.8\\bin\\cudart64_12.dll]" Exception 0xc0000005 0x0 0x3d18 0x7ffc1958f5ca PC=0x7ffc1958f5ca signal arrived during external code execution runtime.cgocall(0x7ff6496b0720, 0xc000520c08) runtime/cgocall.go:167 +0x3e fp=0xc000520be0 sp=0xc000520b78 pc=0x7ff6488f9c3e github.com/ollama/ollama/discover._Cfunc_cudart_init(0x280a83e60e0, 0xc0000fe300) ``` Server crashed during initialization. What's the output of `nvidia-smi`?
GiteaMirror commented 2026-05-04 11:48:17 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Feb 7, 2025):

Your NVIDIA driver version (462.96) is from 2022. Please update your drivers

<!-- gh-comment-id:2644122988 --> @mxyng commented on GitHub (Feb 7, 2025): Your NVIDIA driver version (462.96) is from 2022. Please update your drivers
GiteaMirror commented 2026-05-04 11:48:17 -05:00
Author
Owner
Copy Link

@ShaneK6079 commented on GitHub (Feb 7, 2025):

Yes I updated to 572.16 and it works well now.

One note: I had to manually uninstall all the old drivers and hard-reboot. I thought I had previously upgraded but the new drivers didn't replace the old ones correctly.

Thank you for your help!

<!-- gh-comment-id:2644168441 --> @ShaneK6079 commented on GitHub (Feb 7, 2025): Yes I updated to 572.16 and it works well now. One note: I had to manually uninstall all the old drivers and hard-reboot. I thought I had previously upgraded but the new drivers didn't replace the old ones correctly. Thank you for your 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 bug gpu nvidia windows
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#67824
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?