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 #10830] Remove num_ctx parameter from mistral-small3.1:latest modelfile #7111

New Issue
Open
opened 2026-04-12 19:05:55 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 19:05:55 -05:00
Owner
Copy Link

Originally created by @dguembel-itomig on GitHub (May 23, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10830

The model file for Mistral Small 3.1 sets the number of context tokens to 4096 explicitly. This is atypical, as most other model files do not set this parameter in such a manner. Additionally, it cannot be overridden using an environment variable. Cf. #10829 for an example of the side-effects.

I suggest removing that setting from the model file, in order to make behavior consistent with mistrall-small:latest (and many other model's modelfiles :)

# docker exec -it watchtower-ollama-1 ollama run mistral-small3.1:latest 
>>> /show parameters
Model defined parameters:
num_ctx                        4096
Originally created by @dguembel-itomig on GitHub (May 23, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10830 The model file for Mistral Small 3.1 sets the number of context tokens to 4096 explicitly. This is atypical, as most other model files do not set this parameter in such a manner. Additionally, it cannot be overridden using an environment variable. Cf. #10829 for an example of the side-effects. I suggest removing that setting from the model file, in order to make behavior consistent with mistrall-small:latest (and many other model's modelfiles :) ``` # docker exec -it watchtower-ollama-1 ollama run mistral-small3.1:latest >>> /show parameters Model defined parameters: num_ctx 4096 ```
GiteaMirror added the model label 2026-04-12 19:05:55 -05:00
GiteaMirror commented 2026-04-12 19:05:57 -05:00
Author
Owner
Copy Link

@stephanepoinsart commented on GitHub (May 27, 2025):

I'm running into exactly the same problem, i was about to post the same ticket found yours that describe it perfectly.

We know it runs well at larger context if its forced by some ollama-protocol clients (Open WebUI), but we have some Open-AI compatible clients that are affected.

<!-- gh-comment-id:2914352461 --> @stephanepoinsart commented on GitHub (May 27, 2025): I'm running into exactly the same problem, i was about to post the same ticket found yours that describe it perfectly. We know it runs well at larger context if its forced by some ollama-protocol clients (Open WebUI), but we have some Open-AI compatible clients that are affected.
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 model
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#7111
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?