github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1174] The wizardcoder models request too much memory at load time #62635

New Issue
Closed
opened 2026-05-03 09:50:57 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 09:50:57 -05:00
Owner
Copy Link

Originally created by @Nan-Do on GitHub (Nov 17, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1174

Originally assigned to: @BruceMacD on GitHub.

The context size given to llama.cpp to load this model is 4096, this requires around 10 GB of memory for the context alone, and if we add the 4.5 GB required for the 7B model it's unfeasible to use it in most consumer grade GPUs (and any system without more than 16 GB of ram). In contrast the context size given to codellama, the model from which wizardcoder derives, is 2048.

Originally created by @Nan-Do on GitHub (Nov 17, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1174 Originally assigned to: @BruceMacD on GitHub. The context size given to llama.cpp to load this model is 4096, this requires around 10 GB of memory for the context alone, and if we add the 4.5 GB required for the 7B model it's unfeasible to use it in most consumer grade GPUs (and any system without more than 16 GB of ram). In contrast the context size given to codellama, the model from which wizardcoder derives, is 2048.
GiteaMirror added the bug label 2026-05-03 09:50:57 -05:00
GiteaMirror commented 2026-05-03 09:50:59 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 9, 2024):

Hi there, we've made a ton of improvements to memory allocation and this should be fixed now.

Do note that some models require more memory for larger context windows due to their architecture

<!-- gh-comment-id:2103577417 --> @jmorganca commented on GitHub (May 9, 2024): Hi there, we've made a ton of improvements to memory allocation and this should be fixed now. Do note that some models require more memory for larger context windows due to their architecture
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#62635
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?