github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7475] Ollama uses more ram when trying to load a model for Zed #51262

New Issue
Closed
opened 2026-04-28 19:06:25 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 19:06:25 -05:00
Owner
Copy Link

Originally created by @sophie-s1 on GitHub (Nov 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7475

What is the issue?

Loading models via Zed uses 6GB more ram than the same model does when loaded via Ollama's terminal interface (3GB+model vs 9GB + model)

OS

Linux

GPU

Intel

CPU

Intel

Ollama version

0.3.12

Originally created by @sophie-s1 on GitHub (Nov 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7475 ### What is the issue? Loading models via Zed uses 6GB more ram than the same model does when loaded via Ollama's terminal interface (3GB+model vs 9GB + model) ### OS Linux ### GPU Intel ### CPU Intel ### Ollama version 0.3.12
GiteaMirror added the bug label 2026-04-28 19:06:25 -05:00
GiteaMirror commented 2026-04-28 19:06:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 3, 2024):

Server logs will show for sure, but as a guess I'd say zed is using a larger context window than the default of 2048.

<!-- gh-comment-id:2453379911 --> @rick-github commented on GitHub (Nov 3, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will show for sure, but as a guess I'd say zed is using a larger context window than the default of 2048.
GiteaMirror commented 2026-04-28 19:06:31 -05:00
Author
Owner
Copy Link

@sophie-s1 commented on GitHub (Nov 3, 2024):

llama_new_context_with_model: n_ctx      = 65536
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 500000.0
llama_new_context_with_model: freq_scale = 1

Oh OK, Thanks

<!-- gh-comment-id:2453451203 --> @sophie-s1 commented on GitHub (Nov 3, 2024): ``` llama_new_context_with_model: n_ctx = 65536 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 ``` Oh OK, Thanks
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#51262
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?