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 #9189] Ollama call failed with status code 500: error starting runner: open NUL: The system cannot find the file specified. #5988

New Issue
Open
opened 2026-04-12 17:20:33 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-12 17:20:33 -05:00
Owner
Copy Link

Originally created by @richpei7 on GitHub (Feb 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9189

What is the issue?

I failed to call the deepseek r1 8b and 14b models using page-Assist. I can't find the model files. I'm not sure if this is a BUG

Relevant log output

time=2025-02-18T16:39:03.297+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e gpu=GPU-156d0f1f-11e5-b7e6-47ea-24ecd8e26635 parallel=1 available=11619291136 required="9.2 GiB"
time=2025-02-18T16:39:03.310+08:00 level=INFO source=server.go:100 msg="system memory" total="23.9 GiB" free="17.3 GiB" free_swap="16.3 GiB"
time=2025-02-18T16:39:03.311+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.2 GiB" memory.required.partial="9.2 GiB" memory.required.kv="384.0 MiB" memory.required.allocations="[9.2 GiB]" memory.weights.total="7.7 GiB" memory.weights.repeating="7.1 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB"
time=2025-02-18T16:39:03.320+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62566"
time=2025-02-18T16:39:03.320+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible="[cuda_v12 cuda_v11]"
time=2025-02-18T16:39:03.322+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62567"
time=2025-02-18T16:39:03.322+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible=[cuda_v11]
time=2025-02-18T16:39:03.324+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62568"
time=2025-02-18T16:39:03.324+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e error="error starting runner: open NUL: The system cannot find the file specified. "
[GIN] 2025/02/18 - 16:39:03 | 500 |     91.8684ms |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/02/18 - 16:39:14 | 200 |      2.0562ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/02/18 - 16:39:14 | 200 |      2.0937ms |       127.0.0.1 | GET      "/api/tags"
time=2025-02-18T16:39:16.322+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e gpu=GPU-156d0f1f-11e5-b7e6-47ea-24ecd8e26635 parallel=1 available=11605463040 required="9.2 GiB"
time=2025-02-18T16:39:16.335+08:00 level=INFO source=server.go:100 msg="system memory" total="23.9 GiB" free="17.4 GiB" free_swap="16.4 GiB"
time=2025-02-18T16:39:16.336+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.2 GiB" memory.required.partial="9.2 GiB" memory.required.kv="384.0 MiB" memory.required.allocations="[9.2 GiB]" memory.weights.total="7.7 GiB" memory.weights.repeating="7.1 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB"
time=2025-02-18T16:39:16.345+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62576"
time=2025-02-18T16:39:16.345+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible="[cuda_v12 cuda_v11]"
time=2025-02-18T16:39:16.347+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62577"
time=2025-02-18T16:39:16.347+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible=[cuda_v11]
time=2025-02-18T16:39:16.349+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62578"
time=2025-02-18T16:39:16.349+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e error="error starting runner: open NUL: The system cannot find the file specified. "
[GIN] 2025/02/18 - 16:39:16 | 500 |     96.9948ms |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/02/18 - 16:40:18 | 200 |      2.0637ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/02/18 - 16:40:18 | 200 |      2.5902ms |       127.0.0.1 | GET      "/api/tags"

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

No response

Originally created by @richpei7 on GitHub (Feb 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9189 ### What is the issue? I failed to call the deepseek r1 8b and 14b models using page-Assist. I can't find the model files. I'm not sure if this is a BUG ### Relevant log output ```shell time=2025-02-18T16:39:03.297+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e gpu=GPU-156d0f1f-11e5-b7e6-47ea-24ecd8e26635 parallel=1 available=11619291136 required="9.2 GiB" time=2025-02-18T16:39:03.310+08:00 level=INFO source=server.go:100 msg="system memory" total="23.9 GiB" free="17.3 GiB" free_swap="16.3 GiB" time=2025-02-18T16:39:03.311+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.2 GiB" memory.required.partial="9.2 GiB" memory.required.kv="384.0 MiB" memory.required.allocations="[9.2 GiB]" memory.weights.total="7.7 GiB" memory.weights.repeating="7.1 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB" time=2025-02-18T16:39:03.320+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62566" time=2025-02-18T16:39:03.320+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible="[cuda_v12 cuda_v11]" time=2025-02-18T16:39:03.322+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62567" time=2025-02-18T16:39:03.322+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible=[cuda_v11] time=2025-02-18T16:39:03.324+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62568" time=2025-02-18T16:39:03.324+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e error="error starting runner: open NUL: The system cannot find the file specified. " [GIN] 2025/02/18 - 16:39:03 | 500 | 91.8684ms | 127.0.0.1 | POST "/api/chat" [GIN] 2025/02/18 - 16:39:14 | 200 | 2.0562ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/02/18 - 16:39:14 | 200 | 2.0937ms | 127.0.0.1 | GET "/api/tags" time=2025-02-18T16:39:16.322+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e gpu=GPU-156d0f1f-11e5-b7e6-47ea-24ecd8e26635 parallel=1 available=11605463040 required="9.2 GiB" time=2025-02-18T16:39:16.335+08:00 level=INFO source=server.go:100 msg="system memory" total="23.9 GiB" free="17.4 GiB" free_swap="16.4 GiB" time=2025-02-18T16:39:16.336+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[10.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.2 GiB" memory.required.partial="9.2 GiB" memory.required.kv="384.0 MiB" memory.required.allocations="[9.2 GiB]" memory.weights.total="7.7 GiB" memory.weights.repeating="7.1 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB" time=2025-02-18T16:39:16.345+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62576" time=2025-02-18T16:39:16.345+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible="[cuda_v12 cuda_v11]" time=2025-02-18T16:39:16.347+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62577" time=2025-02-18T16:39:16.347+08:00 level=WARN source=server.go:411 msg="unable to start runner with compatible gpu" error="error starting runner: open NUL: The system cannot find the file specified. " compatible=[cuda_v11] time=2025-02-18T16:39:16.349+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e --ctx-size 2048 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 1 --port 62578" time=2025-02-18T16:39:16.349+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=C:\Users\Administrator\.ollama\models\blobs\sha256-6e9f90f02bb3b39b59e81916e8cfce9deb45aeaeb9a54a5be4414486b907dc1e error="error starting runner: open NUL: The system cannot find the file specified. " [GIN] 2025/02/18 - 16:39:16 | 500 | 96.9948ms | 127.0.0.1 | POST "/api/chat" [GIN] 2025/02/18 - 16:40:18 | 200 | 2.0637ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/02/18 - 16:40:18 | 200 | 2.5902ms | 127.0.0.1 | GET "/api/tags" ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 17:20:33 -05:00
GiteaMirror commented 2026-04-12 17:20:34 -05:00
Author
Owner
Copy Link

@richpei7 commented on GitHub (Feb 18, 2025):

The latest version of Ollama

<!-- gh-comment-id:2665176962 --> @richpei7 commented on GitHub (Feb 18, 2025): The latest version of Ollama
GiteaMirror commented 2026-04-12 17:20:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 18, 2025):

How are you running the server? Do you run ollama serve in a terminal, run it from the start menu, or let it be automatically started on system boot?

<!-- gh-comment-id:2665559401 --> @rick-github commented on GitHub (Feb 18, 2025): How are you running the server? Do you run `ollama serve` in a terminal, run it from the start menu, or let it be automatically started on system boot?
GiteaMirror commented 2026-04-12 17:20:35 -05:00
Author
Owner
Copy Link

@richpei7 commented on GitHub (Feb 19, 2025):

Yes, I was running it from the terminal because opening ollama in the start menu didn't work, it showed that I couldn't connect to ollama, so I used the terminal to start the ollama service, and after I reinstalled my win10 system today and disabled the ollama boot startup, I ran ollama from the terminal, and it still showed that it couldn't be invoked

<!-- gh-comment-id:2667754384 --> @richpei7 commented on GitHub (Feb 19, 2025): Yes, I was running it from the terminal because opening ollama in the start menu didn't work, it showed that I couldn't connect to ollama, so I used the terminal to start the ollama service, and after I reinstalled my win10 system today and disabled the ollama boot startup, I ran ollama from the terminal, and it still showed that it couldn't be invoked
GiteaMirror commented 2026-04-12 17:20:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 19, 2025):

Please add the errors you are receiving.

<!-- gh-comment-id:2667987439 --> @rick-github commented on GitHub (Feb 19, 2025): Please add the errors you are receiving.
GiteaMirror commented 2026-04-12 17:20:35 -05:00
Author
Owner
Copy Link

@richpei7 commented on GitHub (Feb 19, 2025):

Image

Image
Image

<!-- gh-comment-id:2668041392 --> @richpei7 commented on GitHub (Feb 19, 2025): ![Image](https://github.com/user-attachments/assets/d7c408de-df49-4f5e-8fab-35f535ba62d9) ![Image](https://github.com/user-attachments/assets/84a39c46-05b4-4705-b3c6-8608cd6f3b79) ![Image](https://github.com/user-attachments/assets/1b783342-8ad9-4309-a397-f6f0453ff5e1)
GiteaMirror commented 2026-04-12 17:20:36 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 19, 2025):

What errors do you receive when you try to run ollama from the start menu? See app.log and server.log.

<!-- gh-comment-id:2668051802 --> @rick-github commented on GitHub (Feb 19, 2025): What errors do you receive when you try to run ollama from the start menu? See app.log and server.log.
GiteaMirror commented 2026-04-12 17:20:36 -05:00
Author
Owner
Copy Link

@richpei7 commented on GitHub (Feb 20, 2025):

Image
This is a screenshot from the start menu. I also tried the content https://github.com/n4ze3m/page-assist/blob/main/docs/connection-issue.md of this page.
But it does not work, using the start menu still can not connect ollama

<!-- gh-comment-id:2670226136 --> @richpei7 commented on GitHub (Feb 20, 2025): ![Image](https://github.com/user-attachments/assets/e9fd5b35-7a78-437e-bf3a-87f86289eb68) This is a screenshot from the start menu. I also tried the content https://github.com/n4ze3m/page-assist/blob/main/docs/connection-issue.md of this page. But it does not work, using the start menu still can not connect ollama
GiteaMirror commented 2026-04-12 17:20:36 -05:00
Author
Owner
Copy Link

@richpei7 commented on GitHub (Feb 20, 2025):

What errors do you receive when you try to run ollama from the start menu? See app.log and server.log.

Image
The prompt always appears when I download the model

<!-- gh-comment-id:2670699455 --> @richpei7 commented on GitHub (Feb 20, 2025): > What errors do you receive when you try to run ollama from the start menu? See app.log and server.log. ![Image](https://github.com/user-attachments/assets/95b02e56-59b6-40d3-9bd2-4bfd5bb3489c) The prompt always appears when I download the model
GiteaMirror commented 2026-04-12 17:20:37 -05:00
Author
Owner
Copy Link

@daichujie commented on GitHub (Mar 10, 2025):

What errors do you receive when you try to run ollama from the start menu? See app.log and server.log.当您尝试从开始菜单运行 ollama 时，您会收到什么错误？请参阅 app.log 和 server.log。

Image The prompt always appears when I download the model下载模型时总是出现提示

I'm running into this issue as well，Has anyone solved it

<!-- gh-comment-id:2709328500 --> @daichujie commented on GitHub (Mar 10, 2025): > > What errors do you receive when you try to run ollama from the start menu? See app.log and server.log.当您尝试从开始菜单运行 ollama 时，您会收到什么错误？请参阅 app.log 和 server.log。 > > ![Image](https://github.com/user-attachments/assets/95b02e56-59b6-40d3-9bd2-4bfd5bb3489c) The prompt always appears when I download the model下载模型时总是出现提示 I'm running into this issue as well，Has anyone solved it
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#5988
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?