github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4392] Use GTT memory in case of iGPUs to run the model efiiciently. #28504

New Issue
Closed
opened 2026-04-22 06:44:05 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 06:44:05 -05:00
Owner
Copy Link

Originally created by @CoolnsX on GitHub (May 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4392

Models run on System memory using CPU is perfectly fine.

But when using integrate GPUs which have limited VRAM locked by vendors, we have model crash due to "low vram memory"

They have feature called GTT memory on linux, and Shared Memory on windows, which they can use whenever their VRAM capacity is nearly full.

Originally created by @CoolnsX on GitHub (May 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4392 Models run on System memory using CPU is perfectly fine. But when using integrate GPUs which have limited VRAM locked by vendors, we have model crash due to "low vram memory" They have feature called GTT memory on linux, and Shared Memory on windows, which they can use whenever their VRAM capacity is nearly full.
GiteaMirror added the feature request label 2026-04-22 06:44:05 -05:00
GiteaMirror commented 2026-04-22 06:44:07 -05:00
Author
Owner
Copy Link

@robertvazan commented on GitHub (Nov 2, 2024):

See #6282

<!-- gh-comment-id:2453092879 --> @robertvazan commented on GitHub (Nov 2, 2024): See #6282
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#28504
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?