github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9876] "/set parameter num_ctx 1024 " then n_ctx from 8192 to 4096 #6465

New Issue
Closed
opened 2026-04-12 18:01:41 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 18:01:41 -05:00
Owner
Copy Link

Originally created by @fivem on GitHub (Mar 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9876

What is the issue?

ollama run deepseek-r1:32b

------- log -------
llama_init_from_model: n_seq_max = 4
llama_init_from_model: n_ctx = 8192
llama_init_from_model: n_ctx_per_seq = 2048
llama_init_from_model: n_batch = 2048
llama_init_from_model: n_ubatch = 512

then
/set parameter num_ctx 1024

------- log -------
llama_init_from_model: n_seq_max = 4
llama_init_from_model: n_ctx = 4096
llama_init_from_model: n_ctx_per_seq = 1024
llama_init_from_model: n_batch = 2048
llama_init_from_model: n_ubatch = 512

Why did n_ctx change from 8192 to 4096?

Relevant log output

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.6.0

Originally created by @fivem on GitHub (Mar 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9876 ### What is the issue? `ollama run deepseek-r1:32b` ------- log ------- llama_init_from_model: n_seq_max = 4 llama_init_from_model: n_ctx = 8192 llama_init_from_model: n_ctx_per_seq = 2048 llama_init_from_model: n_batch = 2048 llama_init_from_model: n_ubatch = 512 -------------------- then `/set parameter num_ctx 1024 ` ------- log ------- llama_init_from_model: n_seq_max = 4 llama_init_from_model: n_ctx = 4096 llama_init_from_model: n_ctx_per_seq = 1024 llama_init_from_model: n_batch = 2048 llama_init_from_model: n_ubatch = 512 -------------------- Why did n_ctx change from 8192 to 4096? ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-04-12 18:01:41 -05:00
GiteaMirror commented 2026-04-12 18:01:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 19, 2025):

n_seq_max * n_ctx_per_seq = 4 * 1024 = 4096

<!-- gh-comment-id:2735134048 --> @rick-github commented on GitHub (Mar 19, 2025): n_seq_max * n_ctx_per_seq = 4 * 1024 = 4096
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#6465
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?