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 #6433] Manage output length? #66080

New Issue
Closed
opened 2026-05-03 23:52:43 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 23:52:43 -05:00
Owner
Copy Link

Originally created by @nic0711 on GitHub (Aug 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6433

Hi. Is it possible to manage the output length?
I use ollama with llama3.1-instruction-8q and fabric.

My problem is that the output is too short and ends the last sentence unfinished.

The biggest/longest output was 1200 characters...

Can I change this?
Thank you.

Originally created by @nic0711 on GitHub (Aug 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6433 Hi. Is it possible to manage the output length? I use ollama with llama3.1-instruction-8q and fabric. My problem is that the output is too short and ends the last sentence unfinished. The biggest/longest output was 1200 characters... Can I change this? Thank you.
GiteaMirror added the question label 2026-05-03 23:52:43 -05:00
GiteaMirror commented 2026-05-03 23:52:52 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Aug 23, 2024):

@nic0711 you can extend the context length. In the CLI you can just type:

>>> /set parameter num_ctx 8192

Which would set the context length to 8192. You will need to have more VRAM (if you're using a GPU) in order to support a larger context otherwise some layers of the model may be offloaded onto your CPU. Llama3.1 can go up to a 128k context length.

<!-- gh-comment-id:2307923840 --> @pdevine commented on GitHub (Aug 23, 2024): @nic0711 you can extend the context length. In the CLI you can just type: ``` >>> /set parameter num_ctx 8192 ``` Which would set the context length to 8192. You will need to have more VRAM (if you're using a GPU) in order to support a larger context otherwise some layers of the model may be offloaded onto your CPU. Llama3.1 can go up to a 128k context length.
GiteaMirror commented 2026-05-03 23:52:53 -05:00
Author
Owner
Copy Link

@DraculaVladimir commented on GitHub (Jun 29, 2025):

@nic0711 you can extend the context length. In the CLI you can just type:

>>> /set parameter num_ctx 8192

Which would set the context length to 8192. You will need to have more VRAM (if you're using a GPU) in order to support a larger context otherwise some layers of the model may be offloaded onto your CPU. Llama3.1 can go up to a 128k context length.

The man had asked for OUTPUT length not for INPUT.

I find your answer inadequate.

<!-- gh-comment-id:3016363491 --> @DraculaVladimir commented on GitHub (Jun 29, 2025): > [@nic0711](https://github.com/nic0711) you can extend the context length. In the CLI you can just type: > > ``` > >>> /set parameter num_ctx 8192 > ``` > > Which would set the context length to 8192. You will need to have more VRAM (if you're using a GPU) in order to support a larger context otherwise some layers of the model may be offloaded onto your CPU. Llama3.1 can go up to a 128k context length. The man had asked for OUTPUT length not for INPUT. I find your answer inadequate.
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 question
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#66080
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?