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 #10488] Can't create model with Modelfile larger than 100 lines. #53410

New Issue
Closed
opened 2026-04-29 03:02:01 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 03:02:01 -05:00
Owner
Copy Link

Originally created by @gkcccvvv on GitHub (Apr 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10488

What is the issue?

working with gemma3:4b, developing technical service responsible AI model.

When I write more than 100lines in Modelfile, "create" command looking works on cmd but ollama chat starts responding as defaults. I delete few lines and ollama start responding regarding to the Modelfile. How can I expand this limit? Performance is in second place in my applicaiton.

Relevant log output

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.6.6

Originally created by @gkcccvvv on GitHub (Apr 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10488 ### What is the issue? working with gemma3:4b, developing technical service responsible AI model. When I write more than 100lines in Modelfile, "create" command looking works on cmd but ollama chat starts responding as defaults. I delete few lines and ollama start responding regarding to the Modelfile. How can I expand this limit? Performance is in second place in my applicaiton. ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.6.6
GiteaMirror added the bug label 2026-04-29 03:02:01 -05:00
GiteaMirror commented 2026-04-29 03:02:05 -05:00
Author
Owner
Copy Link

@ehan1990 commented on GitHub (Apr 29, 2025):

hey @gkcccvvv , your log output section's empty btw. i think you might have forgotten to add the logs. also could you provide the modelfile that doesn't work if possible?

<!-- gh-comment-id:2840244773 --> @ehan1990 commented on GitHub (Apr 29, 2025): hey @gkcccvvv , your log output section's empty btw. i think you might have forgotten to add the logs. also could you provide the modelfile that doesn't work if possible?
GiteaMirror commented 2026-04-29 03:02:05 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 29, 2025):

Which lines do you delete to make it work: SYSTEM, MESSAGE, TEMPLATE, etc?

<!-- gh-comment-id:2840276506 --> @rick-github commented on GitHub (Apr 29, 2025): Which lines do you delete to make it work: SYSTEM, MESSAGE, TEMPLATE, etc?
GiteaMirror commented 2026-04-29 03:02:05 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 29, 2025):

If you haven't adjusted the size of the context window, the system message exceeds the buffer and is discarded. Add PARAMETER num_ctx 8192 to the Modelfile or set OLLAMA_CONTEXT_LENGTH=8192 in the server environment. Change 8192 to whatever you think you need to accommodate the system message and any user/assistant messages.

<!-- gh-comment-id:2840302853 --> @rick-github commented on GitHub (Apr 29, 2025): If you haven't adjusted the size of the [context window](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size), the system message exceeds the buffer and is discarded. Add `PARAMETER num_ctx 8192` to the Modelfile or set `OLLAMA_CONTEXT_LENGTH=8192` in the server environment. Change 8192 to whatever you think you need to accommodate the system message and any user/assistant messages.
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#53410
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?