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 #8143] Codellama 34b runs on CPU instead of GPU #51708

New Issue
Closed
opened 2026-04-28 20:46:55 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 20:46:55 -05:00
Owner
Copy Link

Originally created by @gregory-lebl on GitHub (Dec 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8143

What is the issue?

Hello,
When I try to use Codellama:34b it doesn't run on the GPU but on the CPU. The 7b and 13B models runs on the GPU but not the 34b and 70b.

Any idea?

OS

WSL2

GPU

Nvidia

CPU

Intel

Ollama version

0.4.7

Originally created by @gregory-lebl on GitHub (Dec 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8143 ### What is the issue? Hello, When I try to use Codellama:34b it doesn't run on the GPU but on the CPU. The 7b and 13B models runs on the GPU but not the 34b and 70b. Any idea? ### OS WSL2 ### GPU Nvidia ### CPU Intel ### Ollama version 0.4.7
GiteaMirror added the needs more infobug labels 2026-04-28 20:46:55 -05:00
GiteaMirror commented 2026-04-28 20:46:57 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 17, 2024):

Server logs will aid in debugging.

<!-- gh-comment-id:2549884765 --> @rick-github commented on GitHub (Dec 17, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging.
GiteaMirror commented 2026-04-28 20:46:57 -05:00
Author
Owner
Copy Link

@felixniemeyer commented on GitHub (Dec 18, 2024):

maybe ollama goes for CPU because the models don't fit in your VRAM

<!-- gh-comment-id:2552325067 --> @felixniemeyer commented on GitHub (Dec 18, 2024): maybe ollama goes for CPU because the models don't fit in your VRAM
GiteaMirror commented 2026-04-28 20:46:57 -05:00
Author
Owner
Copy Link

@gregory-lebl commented on GitHub (Dec 26, 2024):

maybe ollama goes for CPU because the models don't fit in your VRAM

That will be an explanation. I see this log when using the 34b model :

Dec 26 13:59:52 DESKTOP-KO76CAD ollama[110]: time=2024-12-26T13:59:52.591+01:00 level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=49 layers.offload=26 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="19.1 GiB" memory.required.partial="10.8 GiB" memory.required.kv="384.0 MiB" memory.required.allocations="[10.8 GiB]" memory.weights.total="17.8 GiB" memory.weights.repeating="17.6 GiB" memory.weights.nonrepeating="205.1 MiB" memory.graph.full="324.0 MiB" memory.graph.partial="348.0 MiB"

And this log for the 7b model:

Dec 26 14:04:40 DESKTOP-KO76CAD ollama[110]: time=2024-12-26T14:04:40.296+01:00 level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="8.7 GiB" memory.required.partial="8.7 GiB" memory.required.kv="4.0 GiB" memory.required.allocations="[8.7 GiB]" memory.weights.total="7.4 GiB" memory.weights.repeating="7.3 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="681.0 MiB"

The 34b model need 19.1 GiB for memory and the 7b need 8.7 GiB. My GPU has only 10.8 GiB available.

<!-- gh-comment-id:2562687259 --> @gregory-lebl commented on GitHub (Dec 26, 2024): > maybe ollama goes for CPU because the models don't fit in your VRAM That will be an explanation. I see this log when using the 34b model : > Dec 26 13:59:52 DESKTOP-KO76CAD ollama[110]: time=2024-12-26T13:59:52.591+01:00 level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=49 layers.offload=26 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="19.1 GiB" memory.required.partial="10.8 GiB" memory.required.kv="384.0 MiB" memory.required.allocations="[10.8 GiB]" memory.weights.total="17.8 GiB" memory.weights.repeating="17.6 GiB" memory.weights.nonrepeating="205.1 MiB" memory.graph.full="324.0 MiB" memory.graph.partial="348.0 MiB" And this log for the 7b model: > Dec 26 14:04:40 DESKTOP-KO76CAD ollama[110]: time=2024-12-26T14:04:40.296+01:00 level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="8.7 GiB" memory.required.partial="8.7 GiB" memory.required.kv="4.0 GiB" memory.required.allocations="[8.7 GiB]" memory.weights.total="7.4 GiB" memory.weights.repeating="7.3 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="681.0 MiB" The 34b model need 19.1 GiB for memory and the 7b need 8.7 GiB. My GPU has only 10.8 GiB available.
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 needs more info
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#51708
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?