github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 04:34:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8009] make is somehow visible that the context size in models is not used by default #5126

New Issue
Closed
opened 2026-04-12 16:13:33 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 16:13:33 -05:00
Owner
Copy Link

Originally created by @fce2 on GitHub (Dec 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8009

This is extremely important, it drove me kind of crazy ("it woked before, what did i do wrong now" ??):
!!! You cant use the native models context size until you activate it manually !!!

manual procedure:
ollama run llama3.2:3b-instruct-q8_0

/set parameter num_ctx 65536
/save llama3.2:3b-instruct-q8_0-65536
/bye

Thanks for this hint, microsuxxor !!

Its also important to know: the model size increases extremely, a llama3.2-3b model cant run on a 4090 anymore:
llama3.2:3b-instruct-q8_0 5.4GB 150tps
llama3.2:3b-instruct-q8_0-4096 6.8GB 146tps
llama3.2:3b-instruct-q8_0-8192 9.6GB 146tps
llama3.2:3b-instruct-q8_0-16384 15.0GB 146tps
llama3.2:3b-instruct-q8_0-32768 9.6GB 150tps
llama3.2:3b-instruct-q8_0-65536 15.0GB 150tps
llama3.2:3b-instruct-q8_0-131072 26.0GB 30tps

Originally created by @fce2 on GitHub (Dec 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8009 This is extremely important, it drove me kind of crazy ("it woked before, what did i do wrong now" ??): !!! You cant use the native models context size until you activate it manually !!! manual procedure: ollama run llama3.2:3b-instruct-q8_0 > /set parameter num_ctx 65536 > /save llama3.2:3b-instruct-q8_0-65536 > /bye Thanks for this hint, microsuxxor !! Its also important to know: the model size increases extremely, a llama3.2-3b model cant run on a 4090 anymore: llama3.2:3b-instruct-q8_0 5.4GB 150tps llama3.2:3b-instruct-q8_0-4096 6.8GB 146tps llama3.2:3b-instruct-q8_0-8192 9.6GB 146tps llama3.2:3b-instruct-q8_0-16384 15.0GB 146tps llama3.2:3b-instruct-q8_0-32768 9.6GB 150tps llama3.2:3b-instruct-q8_0-65536 15.0GB 150tps llama3.2:3b-instruct-q8_0-131072 26.0GB 30tps
GiteaMirror added the feature request label 2026-04-12 16:13:33 -05:00
GiteaMirror commented 2026-04-12 16:13:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 9, 2024):

https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size

<!-- gh-comment-id:2527488507 --> @rick-github commented on GitHub (Dec 9, 2024): https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size
GiteaMirror commented 2026-04-12 16:13:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 14, 2024):

https://github.com/ollama/ollama/issues/6852#issuecomment-2382909355

<!-- gh-comment-id:2543177391 --> @rick-github commented on GitHub (Dec 14, 2024): https://github.com/ollama/ollama/issues/6852#issuecomment-2382909355
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 feature request
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#5126
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?