github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1197] Trying to run ollama on a server #47121

New Issue
Closed
opened 2026-04-28 03:18:26 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-28 03:18:26 -05:00
Owner
Copy Link

Originally created by @621625 on GitHub (Nov 19, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1197

Originally assigned to: @BruceMacD on GitHub.

Hi,

I'm Mr. Mist, a very friendly guy.

I'm trying to run ollama on a server but get this error message. Any ideas and solutions?

llama_new_context_with_model: kv self size = 256.00 MB
llama_new_context_with_model: compute buffer total size = 162.13 MB
2023/11/19 12:07:13 llama.go:438: error starting llama runner: timed out waiting for llama runner to start
2023/11/19 12:07:14 llama.go:430: signal: killed
2023/11/19 12:07:14 llama.go:504: llama runner stopped successfully
[GIN] 2023/11/19 - 12:07:14 | 500 | 4m32s | 127.0.0.1 | POST "/api/generate"
[GIN] 2023/11/19 - 12:18:11 | 200 | 581.303µs | 127.0.0.1 | HEAD "/"
[GIN] 2023/11/19 - 12:18:11 | 200 | 3.32279ms | 127.0.0.1 | GET "/api/tags"

Originally created by @621625 on GitHub (Nov 19, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1197 Originally assigned to: @BruceMacD on GitHub. Hi, I'm Mr. Mist, a very friendly guy. I'm trying to run ollama on a server but get this error message. Any ideas and solutions? llama_new_context_with_model: kv self size = 256.00 MB llama_new_context_with_model: compute buffer total size = 162.13 MB 2023/11/19 12:07:13 llama.go:438: error starting llama runner: timed out waiting for llama runner to start 2023/11/19 12:07:14 llama.go:430: signal: killed 2023/11/19 12:07:14 llama.go:504: llama runner stopped successfully [GIN] 2023/11/19 - 12:07:14 | 500 | 4m32s | 127.0.0.1 | POST "/api/generate" [GIN] 2023/11/19 - 12:18:11 | 200 | 581.303µs | 127.0.0.1 | HEAD "/" [GIN] 2023/11/19 - 12:18:11 | 200 | 3.32279ms | 127.0.0.1 | GET "/api/tags"
GiteaMirror added the bug label 2026-04-28 03:18:26 -05:00
GiteaMirror commented 2026-04-28 03:18:41 -05:00
Author
Owner
Copy Link

@kukidevs commented on GitHub (Nov 19, 2023):

same here
getting "⠼ Error: timed out waiting for llama runner to start" while running "ollama run mistral" on Ubuntu

<!-- gh-comment-id:1817966524 --> @kukidevs commented on GitHub (Nov 19, 2023): same here getting "⠼ Error: timed out waiting for llama runner to start" while running "ollama run mistral" on Ubuntu
GiteaMirror commented 2026-04-28 03:18:45 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Nov 20, 2023):

Hi all, these messages indicate you may not have enough memory to run the models you are trying to load, or your machine does not have adequate resources. The error messages here could be better, sorry about that.

To confirm, what are the specs of the machines you are using?

<!-- gh-comment-id:1819425044 --> @BruceMacD commented on GitHub (Nov 20, 2023): Hi all, these messages indicate you may not have enough memory to run the models you are trying to load, or your machine does not have adequate resources. The error messages here could be better, sorry about that. To confirm, what are the specs of the machines you are using?
GiteaMirror commented 2026-04-28 03:18:51 -05:00
Author
Owner
Copy Link

@Amal-David commented on GitHub (Nov 20, 2023):

Hey, I'm getting the same error for llama2:70b, trying to run it on a G5.2xlarge (32GB RAM, 24GB A10 with 80GB storage and 20GB Available), RAM and GPU didn't seem to peak when observed, do I need more storage?

<!-- gh-comment-id:1819613217 --> @Amal-David commented on GitHub (Nov 20, 2023): Hey, I'm getting the same error for llama2:70b, trying to run it on a G5.2xlarge (32GB RAM, 24GB A10 with 80GB storage and 20GB Available), RAM and GPU didn't seem to peak when observed, do I need more storage?
GiteaMirror commented 2026-04-28 03:18:56 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Dec 4, 2023):

you will need at least 64gb ram to run the 70b model. But there are plenty of other models that will fit in 32GB RAM. Perhaps try the 13b model for llama2?

<!-- gh-comment-id:1839746308 --> @technovangelist commented on GitHub (Dec 4, 2023): you will need at least 64gb ram to run the 70b model. But there are plenty of other models that will fit in 32GB RAM. Perhaps try the 13b model for llama2?
GiteaMirror commented 2026-04-28 03:19:01 -05:00
Author
Owner
Copy Link

@jexom commented on GitHub (Dec 21, 2023):

Having the same issue with dolphin-mixtral and wizard-vicuna-uncensored:30b on a 64gb ram machine running ollama as a docker container on windows. It takes a long time to load and then times out

<!-- gh-comment-id:1865585466 --> @jexom commented on GitHub (Dec 21, 2023): Having the same issue with dolphin-mixtral and wizard-vicuna-uncensored:30b on a 64gb ram machine running ollama as a docker container on windows. It takes a long time to load and then times out
GiteaMirror commented 2026-04-28 03:19:08 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Jan 3, 2024):

We updated all of the models in the last week or so. Try repulling the models and let us know if your problem is solved.

<!-- gh-comment-id:1875711991 --> @technovangelist commented on GitHub (Jan 3, 2024): We updated all of the models in the last week or so. Try repulling the models and let us know if your problem is solved.
GiteaMirror commented 2026-04-28 03:19:17 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 11, 2024):

Thanks to everyone for the information on this one. When this issue was created there were various issues related to memory allocation (over allocating context window, number of layers on the GPU) which have since been resolved. Closing this issue now, if you see any similar problems please open a new issue so they get attention.

<!-- gh-comment-id:1989069444 --> @BruceMacD commented on GitHub (Mar 11, 2024): Thanks to everyone for the information on this one. When this issue was created there were various issues related to memory allocation (over allocating context window, number of layers on the GPU) which have since been resolved. Closing this issue now, if you see any similar problems please open a new issue so they get attention.
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#47121
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?