github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9161] getting errors when running ollama serve on my m1 mac mini after last update a couple days ago #68018

New Issue
Closed
opened 2026-05-04 12:15:54 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-05-04 12:15:54 -05:00
Owner
Copy Link

Originally created by @mac-city on GitHub (Feb 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9161

Originally assigned to: @jmorganca on GitHub.

What is the issue?

it is still working, but would appreciate any help what these errors mean. I don't get any errors when I run: ollama run deepseek-r1:14b, and I didn't get any errors before the last update.

tried uninstalling and re-downloading and running fresh copy, but not difference.

Relevant log output

2025/02/16 20:51:57 routes.go:1186: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/mapes/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]"
time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:432 msg="total blobs: 5"
time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-02-16T20:51:57.943-06:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)"
time=2025-02-16T20:51:57.983-06:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="10.7 GiB" available="10.7 GiB"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.11

Originally created by @mac-city on GitHub (Feb 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9161 Originally assigned to: @jmorganca on GitHub. ### What is the issue? it is still working, but would appreciate any help what these errors mean. I don't get any errors when I run: ollama run deepseek-r1:14b, and I didn't get any errors before the last update. tried uninstalling and re-downloading and running fresh copy, but not difference. ### Relevant log output ```shell 2025/02/16 20:51:57 routes.go:1186: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/mapes/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]" time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:432 msg="total blobs: 5" time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-16T20:51:57.943-06:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)" time=2025-02-16T20:51:57.983-06:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="10.7 GiB" available="10.7 GiB" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.11
GiteaMirror added the question label 2026-05-04 12:15:54 -05:00
GiteaMirror commented 2026-05-04 12:15:56 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 17, 2025):

Hi @mac-city sorry Ollama feels slower now. May I ask how much VRAM you have?

<!-- gh-comment-id:2661888164 --> @jmorganca commented on GitHub (Feb 17, 2025): Hi @mac-city sorry Ollama feels slower now. May I ask how much VRAM you have?
GiteaMirror commented 2026-05-04 12:15:57 -05:00
Author
Owner
Copy Link

@mac-city commented on GitHub (Feb 17, 2025):

Chipset Model: Apple M1
Type: GPU
Bus: Built-In
Total Number of Cores: 8
Vendor: Apple (0x106b)
Metal Support: Metal 3
(unified) Memory: 16 GB
Type: LPDDR4

anxious to try out MLX support coming soon

<!-- gh-comment-id:2661895474 --> @mac-city commented on GitHub (Feb 17, 2025): Chipset Model: Apple M1 Type: GPU Bus: Built-In Total Number of Cores: 8 Vendor: Apple (0x106b) Metal Support: Metal 3 (unified) Memory: 16 GB Type: LPDDR4 anxious to try out MLX support coming soon
GiteaMirror commented 2026-05-04 12:15:57 -05:00
Author
Owner
Copy Link

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

@mac-city thanks! Which errors are you seeing? Or is the performance worse?

<!-- gh-comment-id:2665944803 --> @jmorganca commented on GitHub (Feb 18, 2025): @mac-city thanks! Which errors are you seeing? Or is the performance worse?
GiteaMirror commented 2026-05-04 12:15:57 -05:00
Author
Owner
Copy Link

@mac-city commented on GitHub (Feb 18, 2025):

2025/02/16 20:51:57 routes.go:1186: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/mapes/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]" time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:432 msg="total blobs: 5" time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-16T20:51:57.943-06:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)" time=2025-02-16T20:51:57.983-06:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="10.7 GiB" available="10.7 GiB"

<!-- gh-comment-id:2667009839 --> @mac-city commented on GitHub (Feb 18, 2025): `2025/02/16 20:51:57 routes.go:1186: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/mapes/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]" time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:432 msg="total blobs: 5" time=2025-02-16T20:51:57.943-06:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-16T20:51:57.943-06:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)" time=2025-02-16T20:51:57.983-06:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="10.7 GiB" available="10.7 GiB"`
GiteaMirror commented 2026-05-04 12:15:58 -05:00
Author
Owner
Copy Link

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

What errors are you referring to? There's no errors in the log outputs you attached.

<!-- gh-comment-id:2667048191 --> @mxyng commented on GitHub (Feb 18, 2025): What errors are you referring to? There's no errors in the log outputs you attached.
GiteaMirror commented 2026-05-04 12:15:59 -05:00
Author
Owner
Copy Link

@mac-city commented on GitHub (Feb 18, 2025):

so this is the normal output from issuing the ollama serve command? I never had anything like that on the previous version.

<!-- gh-comment-id:2667106626 --> @mac-city commented on GitHub (Feb 18, 2025): so this is the normal output from issuing the ollama serve command? I never had anything like that on the previous version.
GiteaMirror commented 2026-05-04 12:15:59 -05:00
Author
Owner
Copy Link

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

Yes this is normal. It's not suggested to run ollama serve directly. It should be run either through the desktop app on macOS or Windows, or a service manager such as systemd on linux. These help manage the lifecycle of ollama. Since you're on macOS, I'd strongly suggest using the desktop app

<!-- gh-comment-id:2667159563 --> @mxyng commented on GitHub (Feb 18, 2025): Yes this is normal. It's not suggested to run `ollama serve` directly. It should be run either through the desktop app on macOS or Windows, or a service manager such as systemd on linux. These help manage the lifecycle of ollama. Since you're on macOS, I'd strongly suggest using the desktop app
GiteaMirror commented 2026-05-04 12:16:00 -05:00
Author
Owner
Copy Link

@mac-city commented on GitHub (Feb 18, 2025):

I must not know what I'm doing. desktop app? I go to ollama, download for macOS, it puts a menu in my menubar when launched, and nothing else happens as far as what I would call a desktop app. the only option on the menubar is quit. I interact on the command line after that. then I serve it to my openwebui server on my proxmox server. serve ollama from my m1 mac mini, and interact through browser. this was a test before buying a new m4 mac mini to use as a dedicated ai for my home assistant and open webui.

<!-- gh-comment-id:2667165899 --> @mac-city commented on GitHub (Feb 18, 2025): I must not know what I'm doing. desktop app? I go to ollama, download for macOS, it puts a menu in my menubar when launched, and nothing else happens as far as what I would call a desktop app. the only option on the menubar is quit. I interact on the command line after that. then I serve it to my openwebui server on my proxmox server. serve ollama from my m1 mac mini, and interact through browser. this was a test before buying a new m4 mac mini to use as a dedicated ai for my home assistant and open webui.
GiteaMirror commented 2026-05-04 12:16:02 -05:00
Author
Owner
Copy Link

@PinkyPatel05 commented on GitHub (Mar 20, 2025):

@mac-city make sure to run your commnd with appropriate permissions, try: sudo ollama run deepseek-r1:14b

<!-- gh-comment-id:2739110180 --> @PinkyPatel05 commented on GitHub (Mar 20, 2025): @mac-city make sure to run your commnd with appropriate permissions, try: `sudo ollama run deepseek-r1:14b`
GiteaMirror commented 2026-05-04 12:16:05 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 1, 2025):

@mac-city When Ollama is present in the tray, the server is already running in the background, and ready. Open up a terminal, and you can run commands like ollama run deepseek-r1:14b to start an interactive chat session...

Image
<!-- gh-comment-id:3025878212 --> @dhiltgen commented on GitHub (Jul 1, 2025): @mac-city When Ollama is present in the tray, the server is already running in the background, and ready. Open up a terminal, and you can run commands like `ollama run deepseek-r1:14b` to start an interactive chat session... <img width="617" alt="Image" src="https://github.com/user-attachments/assets/8394cfa3-c553-4554-9b0d-eda6912e3d51" />
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 question
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#68018
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?