github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8385] Cannot list or install models: Connection refused error on Windows 10 #5382

New Issue
Closed
opened 2026-04-12 16:35:52 -05:00 by GiteaMirror · 15 comments
GiteaMirror commented 2026-04-12 16:35:52 -05:00
Owner
Copy Link

Originally created by @inspector3535 on GitHub (Jan 11, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8385

What is the issue?

Greetings,
I'm unable to interact with Ollama on Windows 10. I cannot list models, nor can I install any of them.
Whatever command I try, I receive the following error: even when I type ollama list, the same error appears.
I initially suspected that my server configuration might be causing the issue, but I tried it on different Windows computers, and the problem persists.
I've even tried different installation methods (direct installation, installing via Scoop, Winget, etc.), but the result is always the same.

Head "http://127.0.0.1:11434/": dial tcp 127.0.0.1:11434: connectex: The connection could not be established because the target machine actively rejected it.```
Note: Windows Defender and the firewall are disabled, and the only error I can find in the log is:
"no compatible GPUs were discovered".
The hardware of my server should be sufficient to run at least small models like LLaMA 2-7B or GPT Small.
Additionally, I can successfully run the Ollama server using ollama serve; I can even see the server running in the browser, but I am unable to display, download, or install models.
Thank you in advance for your time and assistance. I would appreciate any guidance on how to resolve this issue.

### OS

Windows

### GPU

Other

### CPU

Intel

### Ollama version

0.5.4
Originally created by @inspector3535 on GitHub (Jan 11, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8385 ### What is the issue? Greetings, I'm unable to interact with Ollama on Windows 10. I cannot list models, nor can I install any of them. Whatever command I try, I receive the following error: even when I type ollama list, the same error appears. I initially suspected that my server configuration might be causing the issue, but I tried it on different Windows computers, and the problem persists. I've even tried different installation methods (direct installation, installing via Scoop, Winget, etc.), but the result is always the same. ```Error: Head "http://127.0.0.1:11434/": dial tcp 127.0.0.1:11434: connectex: The connection could not be established because the target machine actively rejected it.``` Note: Windows Defender and the firewall are disabled, and the only error I can find in the log is: "no compatible GPUs were discovered". The hardware of my server should be sufficient to run at least small models like LLaMA 2-7B or GPT Small. Additionally, I can successfully run the Ollama server using ollama serve; I can even see the server running in the browser, but I am unable to display, download, or install models. Thank you in advance for your time and assistance. I would appreciate any guidance on how to resolve this issue. ### OS Windows ### GPU Other ### CPU Intel ### Ollama version 0.5.4
GiteaMirror added the bug label 2026-04-12 16:35:52 -05:00
GiteaMirror commented 2026-04-12 16:35:55 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2025):

What does the following display:

curl http://localhost:11434/api/version
<!-- gh-comment-id:2585238707 --> @rick-github commented on GitHub (Jan 11, 2025): What does the following display: ``` curl http://localhost:11434/api/version ```
GiteaMirror commented 2026-04-12 16:35:56 -05:00
Author
Owner
Copy Link

@inspector3535 commented on GitHub (Jan 11, 2025):

{"version":"0.5.4"}

<!-- gh-comment-id:2585240683 --> @inspector3535 commented on GitHub (Jan 11, 2025): {"version":"0.5.4"}
GiteaMirror commented 2026-04-12 16:35:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2025):

Ok, so there are no problems convention to the server via localhost. What's the result of

curl http://127.0.0.1:11434/api/version
<!-- gh-comment-id:2585241786 --> @rick-github commented on GitHub (Jan 11, 2025): Ok, so there are no problems convention to the server via localhost. What's the result of ``` curl http://127.0.0.1:11434/api/version ```
GiteaMirror commented 2026-04-12 16:35:57 -05:00
Author
Owner
Copy Link

@inspector3535 commented on GitHub (Jan 11, 2025):

this command: :
curl http://127.0.0.1:11434/api/version
displays the ollama version on terminal while serving:
{"version":"0.5.4"}

<!-- gh-comment-id:2585246731 --> @inspector3535 commented on GitHub (Jan 11, 2025): this command: : curl http://127.0.0.1:11434/api/version displays the ollama version on terminal while serving: {"version":"0.5.4"}
GiteaMirror commented 2026-04-12 16:35:58 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2025):

Ok, wasn't expecting that. What's the output of

ollama -v
<!-- gh-comment-id:2585247926 --> @rick-github commented on GitHub (Jan 11, 2025): Ok, wasn't expecting that. What's the output of ``` ollama -v ```
GiteaMirror commented 2026-04-12 16:35:59 -05:00
Author
Owner
Copy Link

@inspector3535 commented on GitHub (Jan 11, 2025):

ollama version is 0.5.4

<!-- gh-comment-id:2585254949 --> @inspector3535 commented on GitHub (Jan 11, 2025): ollama version is 0.5.4
GiteaMirror commented 2026-04-12 16:36:00 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2025):

Now I'm confused. The client apparently has no problems connecting to the server. What's the output of

curl locahost:11434 http://localhost:11434/api/tags
ollama ps
<!-- gh-comment-id:2585257923 --> @rick-github commented on GitHub (Jan 11, 2025): Now I'm confused. The client apparently has no problems connecting to the server. What's the output of ``` curl locahost:11434 http://localhost:11434/api/tags ollama ps ```
GiteaMirror commented 2026-04-12 16:36:01 -05:00
Author
Owner
Copy Link

@inspector3535 commented on GitHub (Jan 11, 2025):

Microsoft Windows [Version 10.0.19045.5247]
(c) Microsoft Corporation. All rights reserved.

C:\Users\Administrator>curl locahost:11434 http://localhost:11434/api/tags
curl: (6) Could not resolve host: locahost
{"models":[]}
C:\Users\Administrator>ollama ps
NAME ID SIZE PROCESSOR UNTIL

C:\Users\Administrator>

<!-- gh-comment-id:2585261509 --> @inspector3535 commented on GitHub (Jan 11, 2025): Microsoft Windows [Version 10.0.19045.5247] (c) Microsoft Corporation. All rights reserved. C:\Users\Administrator>curl locahost:11434 http://localhost:11434/api/tags curl: (6) Could not resolve host: locahost {"models":[]} C:\Users\Administrator>ollama ps NAME ID SIZE PROCESSOR UNTIL C:\Users\Administrator>
GiteaMirror commented 2026-04-12 16:36:02 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2025):

So this looks like it's working. What's the output of

ollama list
<!-- gh-comment-id:2585262327 --> @rick-github commented on GitHub (Jan 11, 2025): So this looks like it's working. What's the output of ``` ollama list ```
GiteaMirror commented 2026-04-12 16:36:03 -05:00
Author
Owner
Copy Link

@inspector3535 commented on GitHub (Jan 11, 2025):

C:\Users\Administrator>ollama list
NAME ID SIZE MODIFIED

C:\Users\Administrator>

<!-- gh-comment-id:2585266105 --> @inspector3535 commented on GitHub (Jan 11, 2025): C:\Users\Administrator>ollama list NAME ID SIZE MODIFIED C:\Users\Administrator>
GiteaMirror commented 2026-04-12 16:36:04 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2025):

It's working.

<!-- gh-comment-id:2585266538 --> @rick-github commented on GitHub (Jan 11, 2025): It's working.
GiteaMirror commented 2026-04-12 16:36:05 -05:00
Author
Owner
Copy Link

@inspector3535 commented on GitHub (Jan 11, 2025):

well? this is very weard. but before I attempt to list, the error in the subject was acurring even if I try to list models.

<!-- gh-comment-id:2585266969 --> @inspector3535 commented on GitHub (Jan 11, 2025): well? this is very weard. but before I attempt to list, the error in the subject was acurring even if I try to list models.
GiteaMirror commented 2026-04-12 16:36:06 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2025):

Your hardware doesn't have a GPU so you won't get fast inference. Depending on your requirements, I can recommend the qwen2.5 family: it has small but capable models.

<!-- gh-comment-id:2585267861 --> @rick-github commented on GitHub (Jan 11, 2025): Your hardware doesn't have a GPU so you won't get fast inference. Depending on your requirements, I can recommend the [qwen2.5](https://ollama.com/library/qwen2.5) family: it has small but capable models.
GiteaMirror commented 2026-04-12 16:36:07 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 13, 2025):

I'd also recommend llama3.2; both the 1B and 3B models should work fine on your system.

<!-- gh-comment-id:2588013463 --> @pdevine commented on GitHub (Jan 13, 2025): I'd also recommend `llama3.2`; both the 1B and 3B models should work fine on your system.
GiteaMirror commented 2026-04-12 16:36:08 -05:00
Author
Owner
Copy Link

@inspector3535 commented on GitHub (Jan 13, 2025):

hello everyone;
thanks for your valuable comments, I finally figured out how to use it.
I didn't know that I need to run ollama server on a separate command line, then open another command line to interact with ollama (pull models, run, rm.)
again thanks for your model recommendations, i'll pay attention. sure I don't have GPU on my server so i'll try the ones above.

<!-- gh-comment-id:2588079715 --> @inspector3535 commented on GitHub (Jan 13, 2025): hello everyone; thanks for your valuable comments, I finally figured out how to use it. I didn't know that I need to run ollama server on a separate command line, then open another command line to interact with ollama (pull models, run, rm.) again thanks for your model recommendations, i'll pay attention. sure I don't have GPU on my server so i'll try the ones above.
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#5382
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?