github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.5k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11186] Ollama Server ignore num_ctx for Qwen3 model #7373

New Issue
Closed
opened 2026-04-12 19:25:52 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 19:25:52 -05:00
Owner
Copy Link

Originally created by @JpEncausse on GitHub (Jun 24, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11186

What is the issue?

By Design Ollama is an abstraction wrapper to call various Model.
Ollama expose some parameters to set :

  • in the HTTP Request
  • env variables
  • or CLI variable

A parameter like num_ctx can't be set in the HTTP Request and must be set OLLAMA_CONTEXT_LENGTH variable for Qwen3 models.

This is an inconsistent behavior. Please,

  • remove or handle num_ctx for all models
  • handle the same way CLI, HTTP and ENV

Ollama is a generic wrapper, as a user we can't guess a behavior according to a given model.

Relevant log output

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.9.2

Originally created by @JpEncausse on GitHub (Jun 24, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11186 ### What is the issue? By Design Ollama is an abstraction wrapper to call various Model. Ollama expose some parameters to set : - in the HTTP Request - env variables - or CLI variable A parameter like `num_ctx` can't be set in the HTTP Request and must be set OLLAMA_CONTEXT_LENGTH variable for Qwen3 models. This is an inconsistent behavior. Please, - remove or handle num_ctx for all models - handle the same way CLI, HTTP and ENV Ollama is a generic wrapper, as a user we can't guess a behavior according to a given model. ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.9.2
GiteaMirror added the bug label 2026-04-12 19:25:52 -05:00
GiteaMirror commented 2026-04-12 19:25:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 24, 2025):

$ curl localhost:11434/api/generate -d '{"model":"qwen3"}'
{"model":"qwen3","created_at":"2025-06-24T21:19:51.947251954Z","response":"","done":true,"done_reason":"load"}
$ ps wwp$(pidof /usr/bin/ollama) | sed -ne 's/.*\(ctx-size\)/\1/p'
ctx-size 4096 --batch-size 512 --n-gpu-layers 37 --threads 8 --parallel 1 --port 41259
$ curl localhost:11434/api/generate -d '{"model":"qwen3","options":{"num_ctx":12345}}'
{"model":"qwen3","created_at":"2025-06-24T21:22:05.37284232Z","response":"","done":true,"done_reason":"load"}
$ ps wwp$(pidof /usr/bin/ollama) | sed -ne 's/.*\(ctx-size\)/\1/p'
ctx-size 12345 --batch-size 512 --n-gpu-layers 37 --threads 8 --parallel 1 --port 33679
<!-- gh-comment-id:3001924552 --> @rick-github commented on GitHub (Jun 24, 2025): ```console $ curl localhost:11434/api/generate -d '{"model":"qwen3"}' {"model":"qwen3","created_at":"2025-06-24T21:19:51.947251954Z","response":"","done":true,"done_reason":"load"} $ ps wwp$(pidof /usr/bin/ollama) | sed -ne 's/.*\(ctx-size\)/\1/p' ctx-size 4096 --batch-size 512 --n-gpu-layers 37 --threads 8 --parallel 1 --port 41259 $ curl localhost:11434/api/generate -d '{"model":"qwen3","options":{"num_ctx":12345}}' {"model":"qwen3","created_at":"2025-06-24T21:22:05.37284232Z","response":"","done":true,"done_reason":"load"} $ ps wwp$(pidof /usr/bin/ollama) | sed -ne 's/.*\(ctx-size\)/\1/p' ctx-size 12345 --batch-size 512 --n-gpu-layers 37 --threads 8 --parallel 1 --port 33679
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#7373
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?