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 #12316] 0.1.11 - CUDA error: no kernel image is available for execution on the device (GTX 1080, Windows 10) #33943

New Issue
Closed
opened 2026-04-22 17:07:30 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 17:07:30 -05:00
Owner
Copy Link

Originally created by @haimarstaib on GitHub (Sep 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12316

What is the issue?

GPU: GTX 1080 (Pascal, Compute Capability 6.1)
Error: "CUDA error: no kernel image is available for execution on the device"
Version: 0.1.11
Solution by downgrading to 0.1.10
Problem with automatic updates (GUI App)

Relevant log output

server.log:

time=2025-09-17T11:28:38.832+02:00 level=INFO source=server.go:1289 msg="llama runner started in 43.46 seconds"
ggml_cuda_compute_forward: SCALE failed
CUDA error: no kernel image is available for execution on the device
  current device: 0, in function ggml_cuda_compute_forward at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:2568
  err

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.11

Originally created by @haimarstaib on GitHub (Sep 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12316 ### What is the issue? GPU: GTX 1080 (Pascal, Compute Capability 6.1) Error: "CUDA error: no kernel image is available for execution on the device" Version: 0.1.11 Solution by downgrading to 0.1.10 Problem with automatic updates (GUI App) ### Relevant log output ```shell server.log: time=2025-09-17T11:28:38.832+02:00 level=INFO source=server.go:1289 msg="llama runner started in 43.46 seconds" ggml_cuda_compute_forward: SCALE failed CUDA error: no kernel image is available for execution on the device current device: 0, in function ggml_cuda_compute_forward at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:2568 err ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.11
GiteaMirror added the bug label 2026-04-22 17:07:30 -05:00
GiteaMirror commented 2026-04-22 17:07:31 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 17, 2025):

I believe this is already fixed in main.

cc @dhiltgen

<!-- gh-comment-id:3304442671 --> @pdevine commented on GitHub (Sep 17, 2025): I believe this is already fixed in `main`. cc @dhiltgen
GiteaMirror commented 2026-04-22 17:07:32 -05:00
Author
Owner
Copy Link

@HiRahmatDev commented on GitHub (Sep 18, 2025):

I’d like to add that this issue also occurs on other Pascal GPUs, specifically the GTX 1050 (Compute Capability 6.1) on Windows 11.
Symptoms observed:

  • CUDA error in ggml-cuda.cu when the model starts running
  • llama runner process terminates immediately with exit status 0xc0000409
  • Internal Ollama connection (wsarecv) is closed because the model process crashes
    NVIDIA drivers are up to date, CUDA runtime is installed, and the model used is relatively small qwen3:4b (≤4B), yet the error persists.
    This appears to be related to the latest Ollama build not including support for Compute Capability 6.1, similar to what GTX 1080 users are experiencing in this report.
<!-- gh-comment-id:3306906772 --> @HiRahmatDev commented on GitHub (Sep 18, 2025): I’d like to add that this issue also occurs on other Pascal GPUs, specifically the GTX 1050 (Compute Capability 6.1) on Windows 11. Symptoms observed: - CUDA error in ggml-cuda.cu when the model starts running - llama runner process terminates immediately with exit status 0xc0000409 - Internal Ollama connection (wsarecv) is closed because the model process crashes NVIDIA drivers are up to date, CUDA runtime is installed, and the model used is relatively small qwen3:4b (≤4B), yet the error persists. This appears to be related to the latest Ollama build not including support for Compute Capability 6.1, similar to what GTX 1080 users are experiencing in this report.
GiteaMirror commented 2026-04-22 17:07:32 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 18, 2025):

This is fixed in the next release. 0.12.0. (RC available for download now)

<!-- gh-comment-id:3309838579 --> @dhiltgen commented on GitHub (Sep 18, 2025): This is fixed in the next release. 0.12.0. (RC available for download now)
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#33943
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?