github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6157] always "Error: something went wrong, please see the ollama server logs for details" but no useful info in service log #3845

New Issue
Closed
opened 2026-04-12 14:41:02 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 14:41:02 -05:00
Owner
Copy Link

Originally created by @EachSheep on GitHub (Aug 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6157

What is the issue?

I encountered an insufficient storage space error while downloading llama3.1:70b-instruct-fp16. To resolve this, I backed up the files from /usr/share/ollama/.ollama/models to another drive with more space, located at /users/shared/ollama/.ollama/models, and configured /etc/systemd/system/ollama.service.d/override_ollama.service as follows:

[Service]
Environment="OLLAMA_HOST=0.0.0.0:11434"
Environment="OLLAMA_KEEP_ALIVE=5m"
Environment="OLLAMA_MODELS=/users/shared/ollama/.ollama/models"

Then, I deleted the original /usr/share/ollama/ directory, recreated the /usr/share/ollama directory, and changed its owner and group with sudo chown ollama:ollama /usr/share/ollama. After that, I reloaded the service configuration and restarted the service using sudo systemctl daemon-reload and sudo systemctl restart ollama.

However, when running ollama list, I continuously received an error, as did other ollama commands, stating Error: something went wrong, please see the ollama server logs for details.

I checked the ollama logs using sudo journalctl -u ollama.service > ollama_logs.txt. The logs after restarting the service were:

Aug 04 07:24:50 node2 systemd[1]: Stopping Ollama Service...
Aug 04 07:24:50 node2 systemd[1]: ollama.service: Succeeded.
Aug 04 07:24:50 node2 systemd[1]: Stopped Ollama Service.
Aug 04 07:24:50 node2 systemd[1]: Started Ollama Service.
Aug 04 07:24:50 node2 ollama[78522]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key.
Aug 04 07:24:50 node2 ollama[78522]: Your new public key is:
Aug 04 07:24:50 node2 ollama[78522]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIN8ECjLBExZOAz8FOGXuADTif9I8RIatZmmI11P2TzCh
Aug 04 07:24:50 node2 ollama[78522]: 2024/08/04 07:24:50 routes.go:1108: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS=/users/shared/ollama/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:781 msg="total blobs: 14"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:788 msg="total unused blobs removed: 0"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=routes.go:1155 msg="Listening on [::]:11434 (version 0.3.3)"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama873184855/runners

There are no other error messages. This issue has been troubling me for half a day, and I am quite frustrated. I hope you can help me look into it.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.3

Originally created by @EachSheep on GitHub (Aug 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6157 ### What is the issue? I encountered an insufficient storage space error while downloading llama3.1:70b-instruct-fp16. To resolve this, I backed up the files from `/usr/share/ollama/.ollama/models` to another drive with more space, located at `/users/shared/ollama/.ollama/models`, and configured `/etc/systemd/system/ollama.service.d/override_ollama.service` as follows: ``` [Service] Environment="OLLAMA_HOST=0.0.0.0:11434" Environment="OLLAMA_KEEP_ALIVE=5m" Environment="OLLAMA_MODELS=/users/shared/ollama/.ollama/models" ``` Then, I deleted the original `/usr/share/ollama/` directory, recreated the `/usr/share/ollama` directory, and changed its owner and group with `sudo chown ollama:ollama /usr/share/ollama`. After that, I reloaded the service configuration and restarted the service using `sudo systemctl daemon-reload` and `sudo systemctl restart ollama`. However, when running `ollama list`, I continuously received an error, as did other `ollama` commands, stating `Error: something went wrong, please see the ollama server logs for details`. I checked the `ollama` logs using `sudo journalctl -u ollama.service > ollama_logs.txt`. The logs after restarting the service were: ``` Aug 04 07:24:50 node2 systemd[1]: Stopping Ollama Service... Aug 04 07:24:50 node2 systemd[1]: ollama.service: Succeeded. Aug 04 07:24:50 node2 systemd[1]: Stopped Ollama Service. Aug 04 07:24:50 node2 systemd[1]: Started Ollama Service. Aug 04 07:24:50 node2 ollama[78522]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Aug 04 07:24:50 node2 ollama[78522]: Your new public key is: Aug 04 07:24:50 node2 ollama[78522]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIN8ECjLBExZOAz8FOGXuADTif9I8RIatZmmI11P2TzCh Aug 04 07:24:50 node2 ollama[78522]: 2024/08/04 07:24:50 routes.go:1108: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS=/users/shared/ollama/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:781 msg="total blobs: 14" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:788 msg="total unused blobs removed: 0" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=routes.go:1155 msg="Listening on [::]:11434 (version 0.3.3)" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama873184855/runners ``` There are no other error messages. This issue has been troubling me for half a day, and I am quite frustrated. I hope you can help me look into it. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.3
GiteaMirror added the bug label 2026-04-12 14:41:02 -05:00
GiteaMirror commented 2026-04-12 14:41:03 -05:00
Author
Owner
Copy Link

@EachSheep commented on GitHub (Aug 4, 2024):

New log is below:

Aug 04 07:22:15 node2 systemd[1]: Stopped Ollama Service.
Aug 04 07:22:15 node2 systemd[1]: Started Ollama Service.
Aug 04 07:22:15 node2 ollama[76193]: 2024/08/04 07:22:15 routes.go:1108: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/users/shared/ollama/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.153Z level=INFO source=images.go:781 msg="total blobs: 14"
Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.153Z level=INFO source=images.go:788 msg="total unused blobs removed: 0"
Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.154Z level=INFO source=routes.go:1155 msg="Listening on [::]:11434 (version 0.3.3)"
Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.154Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama2152502762/runners
Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.148Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]"
Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.148Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.940Z level=INFO source=types.go:105 msg="inference compute" id=GPU-8daf251b-5abe-a014-5693-2158b0b56116 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB"
Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.940Z level=INFO source=types.go:105 msg="inference compute" id=GPU-da045543-85a8-23ab-e23a-4fc7809ede22 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB"
Aug 04 07:24:50 node2 systemd[1]: Stopping Ollama Service...
Aug 04 07:24:50 node2 systemd[1]: ollama.service: Succeeded.
Aug 04 07:24:50 node2 systemd[1]: Stopped Ollama Service.
Aug 04 07:24:50 node2 systemd[1]: Started Ollama Service.
Aug 04 07:24:50 node2 ollama[78522]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key.
Aug 04 07:24:50 node2 ollama[78522]: Your new public key is:
Aug 04 07:24:50 node2 ollama[78522]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIN8ECjLBExZOAz8FOGXuADTif9I8RIatZmmI11P2TzCh
Aug 04 07:24:50 node2 ollama[78522]: 2024/08/04 07:24:50 routes.go:1108: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/users/shared/ollama/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:781 msg="total blobs: 14"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:788 msg="total unused blobs removed: 0"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=routes.go:1155 msg="Listening on [::]:11434 (version 0.3.3)"
Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama873184855/runners
Aug 04 07:24:55 node2 ollama[78522]: time=2024-08-04T07:24:55.902Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]"
Aug 04 07:24:55 node2 ollama[78522]: time=2024-08-04T07:24:55.902Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
Aug 04 07:24:56 node2 ollama[78522]: time=2024-08-04T07:24:56.704Z level=INFO source=types.go:105 msg="inference compute" id=GPU-8daf251b-5abe-a014-5693-2158b0b56116 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB"
Aug 04 07:24:56 node2 ollama[78522]: time=2024-08-04T07:24:56.704Z level=INFO source=types.go:105 msg="inference compute" id=GPU-da045543-85a8-23ab-e23a-4fc7809ede22 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB"
<!-- gh-comment-id:2267395821 --> @EachSheep commented on GitHub (Aug 4, 2024): New log is below: ``` Aug 04 07:22:15 node2 systemd[1]: Stopped Ollama Service. Aug 04 07:22:15 node2 systemd[1]: Started Ollama Service. Aug 04 07:22:15 node2 ollama[76193]: 2024/08/04 07:22:15 routes.go:1108: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/users/shared/ollama/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.153Z level=INFO source=images.go:781 msg="total blobs: 14" Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.153Z level=INFO source=images.go:788 msg="total unused blobs removed: 0" Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.154Z level=INFO source=routes.go:1155 msg="Listening on [::]:11434 (version 0.3.3)" Aug 04 07:22:15 node2 ollama[76193]: time=2024-08-04T07:22:15.154Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama2152502762/runners Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.148Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]" Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.148Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs" Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.940Z level=INFO source=types.go:105 msg="inference compute" id=GPU-8daf251b-5abe-a014-5693-2158b0b56116 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB" Aug 04 07:22:20 node2 ollama[76193]: time=2024-08-04T07:22:20.940Z level=INFO source=types.go:105 msg="inference compute" id=GPU-da045543-85a8-23ab-e23a-4fc7809ede22 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB" Aug 04 07:24:50 node2 systemd[1]: Stopping Ollama Service... Aug 04 07:24:50 node2 systemd[1]: ollama.service: Succeeded. Aug 04 07:24:50 node2 systemd[1]: Stopped Ollama Service. Aug 04 07:24:50 node2 systemd[1]: Started Ollama Service. Aug 04 07:24:50 node2 ollama[78522]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Aug 04 07:24:50 node2 ollama[78522]: Your new public key is: Aug 04 07:24:50 node2 ollama[78522]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIN8ECjLBExZOAz8FOGXuADTif9I8RIatZmmI11P2TzCh Aug 04 07:24:50 node2 ollama[78522]: 2024/08/04 07:24:50 routes.go:1108: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/users/shared/ollama/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:781 msg="total blobs: 14" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.954Z level=INFO source=images.go:788 msg="total unused blobs removed: 0" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=routes.go:1155 msg="Listening on [::]:11434 (version 0.3.3)" Aug 04 07:24:50 node2 ollama[78522]: time=2024-08-04T07:24:50.955Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama873184855/runners Aug 04 07:24:55 node2 ollama[78522]: time=2024-08-04T07:24:55.902Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]" Aug 04 07:24:55 node2 ollama[78522]: time=2024-08-04T07:24:55.902Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs" Aug 04 07:24:56 node2 ollama[78522]: time=2024-08-04T07:24:56.704Z level=INFO source=types.go:105 msg="inference compute" id=GPU-8daf251b-5abe-a014-5693-2158b0b56116 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB" Aug 04 07:24:56 node2 ollama[78522]: time=2024-08-04T07:24:56.704Z level=INFO source=types.go:105 msg="inference compute" id=GPU-da045543-85a8-23ab-e23a-4fc7809ede22 library=cuda compute=8.0 driver=12.5 name="NVIDIA A100-PCIE-40GB" total="39.5 GiB" available="39.1 GiB" ```
GiteaMirror commented 2026-04-12 14:41:04 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 4, 2024):

OLLAMA_MODELS just changes the model directory, it's still using the original /usr/share/ollama for the private key. You can either re-create that directory with appropriate permissions, add Environment="HOME=/users/shared/ollama/" to the service file, or usermod -d /users/shared/ollama ollama.

<!-- gh-comment-id:2267455980 --> @rick-github commented on GitHub (Aug 4, 2024): `OLLAMA_MODELS` just changes the model directory, it's still using the original `/usr/share/ollama` for the private key. You can either re-create that directory with appropriate permissions, add `Environment="HOME=/users/shared/ollama/"` to the service file, or `usermod -d /users/shared/ollama ollama`.
GiteaMirror commented 2026-04-12 14:41:04 -05:00
Author
Owner
Copy Link

@EachSheep commented on GitHub (Aug 6, 2024):

Thanks for your reply! I just recreated all the files and everything works fine!

<!-- gh-comment-id:2270448877 --> @EachSheep commented on GitHub (Aug 6, 2024): Thanks for your reply! I just recreated all the files and everything works fine!
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#3845
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?