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 #6602] n_ctx parameter display error #50670

New Issue
Closed
opened 2026-04-28 16:46:15 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 16:46:15 -05:00
Owner
Copy Link

Originally created by @ada-jt1725 on GitHub (Sep 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6602

When I create model from a Modelfile:

FROM mistral:latest
PARAMETER num_ctx 4096

and load with:

ollama create mistral:latest-nctx4096 -f Modelfile
ollama run mistral:latest-nctx4096

setting n_ctx to 4096, it is discovered that on the server end n_ctx is wrongly displayed as 16384:
image

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.3.9

Originally created by @ada-jt1725 on GitHub (Sep 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6602 When I create model from a Modelfile: ```log FROM mistral:latest PARAMETER num_ctx 4096 ``` and load with: ```log ollama create mistral:latest-nctx4096 -f Modelfile ollama run mistral:latest-nctx4096 ``` setting `n_ctx` to 4096, it is discovered that on the server end `n_ctx` is wrongly displayed as `16384`: ![image](https://github.com/user-attachments/assets/c71f4668-40cd-4bcf-b42d-186028eba52a) ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.3.9
GiteaMirror added the bug label 2026-04-28 16:46:15 -05:00
GiteaMirror commented 2026-04-28 16:46:18 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 3, 2024):

You have OLLAMA_NUM_PARALLEL=4, or it's unset, and ollama is using a default value of 4. Each model instance has its own context space. n_ctx is the total space allocated for context, 4 * 4096 = 16384. If you set OLLAMA_NUM_PARALLEL=1 in the server environment, n_ctx will show as 4096.

<!-- gh-comment-id:2326186263 --> @rick-github commented on GitHub (Sep 3, 2024): You have `OLLAMA_NUM_PARALLEL=4`, or it's unset, and ollama is using a default value of 4. Each model instance has its own context space. `n_ctx` is the total space allocated for context, 4 * 4096 = 16384. If you set `OLLAMA_NUM_PARALLEL=1` in the server environment, `n_ctx` will show as 4096.
GiteaMirror commented 2026-04-28 16:46:18 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Sep 3, 2024):

@rick-github is correct. Sorry this isn't more obvious – we'll improve the logging over time :)

<!-- gh-comment-id:2326946650 --> @jmorganca commented on GitHub (Sep 3, 2024): @rick-github is correct. Sorry this isn't more obvious – we'll improve the logging over time :)
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#50670
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?