github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1493] A way to prevent downloaded models from being deleted #805

New Issue
Closed
opened 2026-04-12 10:28:52 -05:00 by GiteaMirror · 19 comments
GiteaMirror commented 2026-04-12 10:28:52 -05:00
Owner
Copy Link

Originally created by @t18n on GitHub (Dec 13, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1493

I downloaded around 50Gbs worth of models to use with Big AGI. For some reason, when I reloaded with Big AGI interface, all the models are gone. The models are too easy to get removed and it takes a lot of time to download them. Is there a way to prevent that? Can I save the models somewhere and point Ollama to it instead?

Originally created by @t18n on GitHub (Dec 13, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1493 I downloaded around 50Gbs worth of models to use with Big AGI. For some reason, when I reloaded with Big AGI interface, all the models are gone. The models are too easy to get removed and it takes a lot of time to download them. Is there a way to prevent that? Can I save the models somewhere and point Ollama to it instead?
GiteaMirror commented 2026-04-12 10:28:53 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Dec 13, 2023):

Hi @t18n, it sounds like there is a chance that the models are still on your system, fully downloaded models shouldn't get deleted automatically.

Try making sure Ollama is running in the same context (as a service versus as the user). You can manually check if the models are still around locally by checking both ~/.ollama/models and /usr/share/ollama/.ollama/models

<!-- gh-comment-id:1854270980 --> @BruceMacD commented on GitHub (Dec 13, 2023): Hi @t18n, it sounds like there is a chance that the models are still on your system, fully downloaded models shouldn't get deleted automatically. Try making sure Ollama is running in the same context (as a service versus as the user). You can manually check if the models are still around locally by checking both `~/.ollama/models` and `/usr/share/ollama/.ollama/models`
GiteaMirror commented 2026-04-12 10:28:53 -05:00
Author
Owner
Copy Link

@t18n commented on GitHub (Dec 13, 2023):

@BruceMacD I checked and it actually seems like they are not deleted. However, when I run ollama list, there is only the latest model showed up
image

<!-- gh-comment-id:1854634160 --> @t18n commented on GitHub (Dec 13, 2023): @BruceMacD I checked and it actually seems like they are not deleted. However, when I run `ollama list`, there is only the latest model showed up ![image](https://github.com/jmorganca/ollama/assets/14198542/f7ebde64-8921-450b-a608-cee96a6f1ff3)
GiteaMirror commented 2026-04-12 10:28:53 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Dec 15, 2023):

@t18n interesting, are there duplicates in /usr/share/ollama/.ollama/models?

<!-- gh-comment-id:1858172076 --> @BruceMacD commented on GitHub (Dec 15, 2023): @t18n interesting, are there duplicates in `/usr/share/ollama/.ollama/models`?
GiteaMirror commented 2026-04-12 10:28:54 -05:00
Author
Owner
Copy Link

@t18n commented on GitHub (Dec 18, 2023):

@BruceMacD I use MacOS 14.0 and there is no /usr/share/ollama/ folder on my computer.

<!-- gh-comment-id:1860386102 --> @t18n commented on GitHub (Dec 18, 2023): @BruceMacD I use MacOS 14.0 and there is no `/usr/share/ollama/` folder on my computer.
GiteaMirror commented 2026-04-12 10:28:54 -05:00
Author
Owner
Copy Link

@t18n commented on GitHub (Dec 18, 2023):

Good news, all the lost models seems to be back and I have no clue why. I did press the Refresh button on Big AGI several times before it shows up though.

image

<!-- gh-comment-id:1860390700 --> @t18n commented on GitHub (Dec 18, 2023): Good news, all the lost models seems to be back and I have no clue why. I did press the `Refresh` button on **Big AGI** several times before it shows up though. ![image](https://github.com/jmorganca/ollama/assets/14198542/3423f6f9-bf3d-4dd1-8404-ceea9f21340a)
GiteaMirror commented 2026-04-12 10:28:54 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 25, 2024):

Going to go ahead and close this since it seems like it got fixed.

<!-- gh-comment-id:1911098569 --> @pdevine commented on GitHub (Jan 25, 2024): Going to go ahead and close this since it seems like it got fixed.
GiteaMirror commented 2026-04-12 10:28:55 -05:00
Author
Owner
Copy Link

@YuanfengZhang commented on GitHub (Mar 25, 2024):

It happened to me several times on my Ubuntu 22.04 machine. And I get the safe way to stop and run ollama:

  1. stop it using systemctl stop ollama.service instead of CTRL+C
  2. start it using ollama serve instead of systemctl restart ollama.service or systemctl start ollama.service

if failed, try another run.

<!-- gh-comment-id:2017659700 --> @YuanfengZhang commented on GitHub (Mar 25, 2024): It happened to me several times on my Ubuntu 22.04 machine. And I get the safe way to stop and run ollama: 1. stop it using `systemctl stop ollama.service` instead of `CTRL+C` 2. start it using `ollama serve` instead of `systemctl restart ollama.service` or `systemctl start ollama.service` if failed, try another run.
GiteaMirror commented 2026-04-12 10:28:55 -05:00
Author
Owner
Copy Link

@kmanan commented on GitHub (Nov 1, 2024):

I'm running into this issue. Ollama and Ollama WebUI installed via Portainer on Ubuntu

<!-- gh-comment-id:2452231802 --> @kmanan commented on GitHub (Nov 1, 2024): I'm running into this issue. Ollama and Ollama WebUI installed via Portainer on Ubuntu
GiteaMirror commented 2026-04-12 10:28:55 -05:00
Author
Owner
Copy Link

@blackpyramid88 commented on GitHub (Feb 20, 2025):

I'm having this problem with a Windows computer running in Command Prompt. I restarted my computer and all the models were gone and I had to download again. When I ran Ollama List I got nothing..... any help would be appreciated

<!-- gh-comment-id:2670700706 --> @blackpyramid88 commented on GitHub (Feb 20, 2025): I'm having this problem with a Windows computer running in Command Prompt. I restarted my computer and all the models were gone and I had to download again. When I ran Ollama List I got nothing..... any help would be appreciated
GiteaMirror commented 2026-04-12 10:28:55 -05:00
Author
Owner
Copy Link

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

I've just had the exact same -- I thought it was my open-webui setup (ollama windows, open-webui docker), updated both then realised the model folders (blobs, manifests) were now empty

<!-- gh-comment-id:2670825621 --> @sebastianlau commented on GitHub (Feb 20, 2025): I've just had the exact same -- I thought it was my open-webui setup (ollama windows, open-webui docker), updated both then realised the model folders (blobs, manifests) were now empty
GiteaMirror commented 2026-04-12 10:28:56 -05:00
Author
Owner
Copy Link

@blackpyramid88 commented on GitHub (Feb 20, 2025):

Image

Image

Image

Image

Image

I spent a week working on my models and created 3 new models to see them all gone. I've tried every command to pull them out of memory, but nothing worked. I travel quite a bit and I'm not sure how I can incorporate my business this way if I keep loosing all of my data. Any help recovering would be appreciated.

UPDATE: Ok I figured out how to find all the models. Run the "ls" command in command prompt once you're in ubuntu. Then load the model back into the memory and it's back! I was afraid I lost it all but I got them all back now! Thanks guys for the help and hopefully these screenshots help anyone else that's new like me and help prevent the frustration I went through!

<!-- gh-comment-id:2671690152 --> @blackpyramid88 commented on GitHub (Feb 20, 2025): ![Image](https://github.com/user-attachments/assets/aeaf3177-df46-4f30-97cc-c08022993db1) ![Image](https://github.com/user-attachments/assets/ce02d440-44a2-44fb-8f67-d9f0a4e8f2b0) ![Image](https://github.com/user-attachments/assets/51decec9-88b1-43a7-81a0-2ee5a52e5e1f) ![Image](https://github.com/user-attachments/assets/85ae13bf-a597-4b57-a04e-a4bf9424f9f4) ![Image](https://github.com/user-attachments/assets/f1f6c737-ae7e-4a94-9fda-074946803ed7) I spent a week working on my models and created 3 new models to see them all gone. I've tried every command to pull them out of memory, but nothing worked. I travel quite a bit and I'm not sure how I can incorporate my business this way if I keep loosing all of my data. Any help recovering would be appreciated. UPDATE: Ok I figured out how to find all the models. Run the "ls" command in command prompt once you're in ubuntu. Then load the model back into the memory and it's back! I was afraid I lost it all but I got them all back now! Thanks guys for the help and hopefully these screenshots help anyone else that's new like me and help prevent the frustration I went through!
GiteaMirror commented 2026-04-12 10:28:56 -05:00
Author
Owner
Copy Link

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

@blackpyramid88 you should check whether they have been deleted from the filesystem, or just from ollama

The default location for models is something like C:\Users<username>\AppData\Local\Ollama\models -- if they're gone from there you may be able to use a file recovery tool (e.g. PhotoRec), but I wouldn't pin my hopes on that. If they still exist in there you can probably re-add them (but I'm not familiar with how)

<!-- gh-comment-id:2671801184 --> @sebastianlau commented on GitHub (Feb 20, 2025): @blackpyramid88 you should check whether they have been deleted from the filesystem, or just from ollama The default location for models is something like _C:\Users\<username>\AppData\Local\Ollama\models_ -- if they're gone from there you may be able to use a file recovery tool (e.g. PhotoRec), but I wouldn't pin my hopes on that. If they still exist in there you can probably re-add them (but I'm not familiar with how)
GiteaMirror commented 2026-04-12 10:28:56 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Feb 21, 2025):

@blackpyramid88 @sebastianlau can you describe exactly what happened? Did you upgrade something? Did you change anything like environment variables?

<!-- gh-comment-id:2673019992 --> @pdevine commented on GitHub (Feb 21, 2025): @blackpyramid88 @sebastianlau can you describe exactly what happened? Did you upgrade something? Did you change anything like environment variables?
GiteaMirror commented 2026-04-12 10:28:56 -05:00
Author
Owner
Copy Link

@sebastianlau commented on GitHub (Feb 21, 2025):

@pdevine AFAIK it' occurred as a result of an upgrade of either ollama or open-webui (I did three updates in quick succession so am not sure when exactly it occurred -- I also could not find anything in the logs related to it)

Host machine is running Windows Server 2022
Using ollama-windows native (uses the tray app/service -- updated via "an update is available, click to restart")
Docker is being hosted here (WSL2 integration) for running open-webui (updated via "docker compose pull/recreate etc")
Nginx is running in another docker container as a reverse proxy to open-webui's container
Models were stored in a different location to default ("D:\ollama")

I think my update path for open-webui was 0.5.4 -> 0.5.14 -> 0.5.15, I started way earlier though so receive the "vacuum db" warning on startup

Env var's have not been changed at all (though I did need to update my nginx.conf to sort out websockets)

<!-- gh-comment-id:2673781526 --> @sebastianlau commented on GitHub (Feb 21, 2025): @pdevine AFAIK it' occurred as a result of an upgrade of either ollama or open-webui (I did three updates in quick succession so am not sure when exactly it occurred -- I also could not find anything in the logs related to it) Host machine is running Windows Server 2022 Using ollama-windows native (uses the tray app/service -- updated via "an update is available, click to restart") Docker is being hosted here (WSL2 integration) for running open-webui (updated via "docker compose pull/recreate etc") Nginx is running in another docker container as a reverse proxy to open-webui's container Models were stored in a different location to default ("D:\ollama\") I think my update path for open-webui was 0.5.4 -> 0.5.14 -> 0.5.15, I started way earlier though so receive the "vacuum db" warning on startup Env var's have not been changed at all (though I did need to update my nginx.conf to sort out websockets)
GiteaMirror commented 2026-04-12 10:28:57 -05:00
Author
Owner
Copy Link

@DewiarQR commented on GitHub (Feb 21, 2025):

I have already deleted all the models twice. Apparently, when fully loaded, there is a moment when Ollama deletes its models for some reason. I have no strength left to install them, my hands are down

<!-- gh-comment-id:2674241065 --> @DewiarQR commented on GitHub (Feb 21, 2025): I have already deleted all the models twice. Apparently, when fully loaded, there is a moment when Ollama deletes its models for some reason. I have no strength left to install them, my hands are down
GiteaMirror commented 2026-04-12 10:28:57 -05:00
Author
Owner
Copy Link

@DewiarQR commented on GitHub (Feb 21, 2025):

dewiar@dewiar:$ systemctl stop ollama.service
Warning: The unit file, source configuration file or drop-ins of ollama.service changed on disk. Run 'systemctl daemon-reload' to reload units.
dewiar@dewiar:$ ollama serve
2025/02/21 14:27:05 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: 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_INTEL_GPU:false 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:/home/dewiar/.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 ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-02-21T14:27:05.297+03:00 level=INFO source=images.go:432 msg="total blobs: 0"
time=2025-02-21T14:27:05.297+03:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.

[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.

  • using env: export GIN_MODE=release
  • using code: gin.SetMode(gin.ReleaseMode)

[GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers)
[GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers)
[GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers)
[GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers)
[GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers)
[GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers)
[GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers)
[GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers)
[GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers)
[GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers)
[GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers)
[GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers)
[GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers)
[GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
[GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
[GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers)
[GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers)
[GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers)
[GIN-debug] GET / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
[GIN-debug] HEAD / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
time=2025-02-21T14:27:05.297+03:00 level=INFO source=routes.go:1238 msg="Listening on 127.0.0.1:11434 (version 0.5.7)"
time=2025-02-21T14:27:05.298+03:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx rocm_avx]"
time=2025-02-21T14:27:05.298+03:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs"
time=2025-02-21T14:27:05.440+03:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-59933eb2-145a-7eb0-60a3-0c0cec1c5c79 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="23.6 GiB" available="23.0 GiB"

<!-- gh-comment-id:2674954025 --> @DewiarQR commented on GitHub (Feb 21, 2025): [dewiar@dewiar](mailto:dewiar@dewiar):~$ systemctl stop ollama.service Warning: The unit file, source configuration file or drop-ins of ollama.service changed on disk. Run 'systemctl daemon-reload' to reload units. [dewiar@dewiar](mailto:dewiar@dewiar):~$ ollama serve 2025/02/21 14:27:05 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: 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_INTEL_GPU:false 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:/home/dewiar/.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 ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-02-21T14:27:05.297+03:00 level=INFO source=images.go:432 msg="total blobs: 0" time=2025-02-21T14:27:05.297+03:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached. [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production. - using env: export GIN_MODE=release - using code: gin.SetMode(gin.ReleaseMode) [GIN-debug] POST /api/pull --> [github.com/ollama/ollama/server.(*Server).PullHandler-fm](http://github.com/ollama/ollama/server.(*Server).PullHandler-fm) (5 handlers) [GIN-debug] POST /api/generate --> [github.com/ollama/ollama/server.(*Server).GenerateHandler-fm](http://github.com/ollama/ollama/server.(*Server).GenerateHandler-fm) (5 handlers) [GIN-debug] POST /api/chat --> [github.com/ollama/ollama/server.(*Server).ChatHandler-fm](http://github.com/ollama/ollama/server.(*Server).ChatHandler-fm) (5 handlers) [GIN-debug] POST /api/embed --> [github.com/ollama/ollama/server.(*Server).EmbedHandler-fm](http://github.com/ollama/ollama/server.(*Server).EmbedHandler-fm) (5 handlers) [GIN-debug] POST /api/embeddings --> [github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm](http://github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm) (5 handlers) [GIN-debug] POST /api/create --> [github.com/ollama/ollama/server.(*Server).CreateHandler-fm](http://github.com/ollama/ollama/server.(*Server).CreateHandler-fm) (5 handlers) [GIN-debug] POST /api/push --> [github.com/ollama/ollama/server.(*Server).PushHandler-fm](http://github.com/ollama/ollama/server.(*Server).PushHandler-fm) (5 handlers) [GIN-debug] POST /api/copy --> [github.com/ollama/ollama/server.(*Server).CopyHandler-fm](http://github.com/ollama/ollama/server.(*Server).CopyHandler-fm) (5 handlers) [GIN-debug] DELETE /api/delete --> [github.com/ollama/ollama/server.(*Server).DeleteHandler-fm](http://github.com/ollama/ollama/server.(*Server).DeleteHandler-fm) (5 handlers) [GIN-debug] POST /api/show --> [github.com/ollama/ollama/server.(*Server).ShowHandler-fm](http://github.com/ollama/ollama/server.(*Server).ShowHandler-fm) (5 handlers) [GIN-debug] POST /api/blobs/:digest --> [github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm](http://github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm) (5 handlers) [GIN-debug] HEAD /api/blobs/:digest --> [github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm](http://github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm) (5 handlers) [GIN-debug] GET /api/ps --> [github.com/ollama/ollama/server.(*Server).PsHandler-fm](http://github.com/ollama/ollama/server.(*Server).PsHandler-fm) (5 handlers) [GIN-debug] POST /v1/chat/completions --> [github.com/ollama/ollama/server.(*Server).ChatHandler-fm](http://github.com/ollama/ollama/server.(*Server).ChatHandler-fm) (6 handlers) [GIN-debug] POST /v1/completions --> [github.com/ollama/ollama/server.(*Server).GenerateHandler-fm](http://github.com/ollama/ollama/server.(*Server).GenerateHandler-fm) (6 handlers) [GIN-debug] POST /v1/embeddings --> [github.com/ollama/ollama/server.(*Server).EmbedHandler-fm](http://github.com/ollama/ollama/server.(*Server).EmbedHandler-fm) (6 handlers) [GIN-debug] GET /v1/models --> [github.com/ollama/ollama/server.(*Server).ListHandler-fm](http://github.com/ollama/ollama/server.(*Server).ListHandler-fm) (6 handlers) [GIN-debug] GET /v1/models/:model --> [github.com/ollama/ollama/server.(*Server).ShowHandler-fm](http://github.com/ollama/ollama/server.(*Server).ShowHandler-fm) (6 handlers) [GIN-debug] GET / --> [github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1](http://github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1) (5 handlers) [GIN-debug] GET /api/tags --> [github.com/ollama/ollama/server.(*Server).ListHandler-fm](http://github.com/ollama/ollama/server.(*Server).ListHandler-fm) (5 handlers) [GIN-debug] GET /api/version --> [github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2](http://github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2) (5 handlers) [GIN-debug] HEAD / --> [github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1](http://github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1) (5 handlers) [GIN-debug] HEAD /api/tags --> [github.com/ollama/ollama/server.(*Server).ListHandler-fm](http://github.com/ollama/ollama/server.(*Server).ListHandler-fm) (5 handlers) [GIN-debug] HEAD /api/version --> [github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2](http://github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2) (5 handlers) time=2025-02-21T14:27:05.297+03:00 level=INFO source=routes.go:1238 msg="Listening on [127.0.0.1:11434](http://127.0.0.1:11434/) (version 0.5.7)" time=2025-02-21T14:27:05.298+03:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx rocm_avx]" time=2025-02-21T14:27:05.298+03:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2025-02-21T14:27:05.440+03:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-59933eb2-145a-7eb0-60a3-0c0cec1c5c79 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="23.6 GiB" available="23.0 GiB"
GiteaMirror commented 2026-04-12 10:28:58 -05:00
Author
Owner
Copy Link

@blackpyramid88 commented on GitHub (Feb 21, 2025):

I have already deleted all the models twice. Apparently, when fully loaded, there is a moment when Ollama deletes its models for some reason. I have no strength left to install them, my hands are down

I just posted screenshots I hope will help you!

<!-- gh-comment-id:2675509071 --> @blackpyramid88 commented on GitHub (Feb 21, 2025): > I have already deleted all the models twice. Apparently, when fully loaded, there is a moment when Ollama deletes its models for some reason. I have no strength left to install them, my hands are down I just posted screenshots I hope will help you!
GiteaMirror commented 2026-04-12 10:28:58 -05:00
Author
Owner
Copy Link

@blackpyramid88 commented on GitHub (Feb 21, 2025):

@blackpyramid88 @sebastianlau can you describe exactly what happened? Did you upgrade something? Did you change anything like environment variables?

When I shut down or restart the computer and restarted it all of my models in Ollama had disappeared from my directory. Now I know to run the ls command and then load the ones I want. Thanks!

<!-- gh-comment-id:2675511739 --> @blackpyramid88 commented on GitHub (Feb 21, 2025): > [@blackpyramid88](https://github.com/blackpyramid88) [@sebastianlau](https://github.com/sebastianlau) can you describe exactly what happened? Did you upgrade something? Did you change anything like environment variables? When I shut down or restart the computer and restarted it all of my models in Ollama had disappeared from my directory. Now I know to run the ls command and then load the ones I want. Thanks!
GiteaMirror commented 2026-04-12 10:28:58 -05:00
Author
Owner
Copy Link

@blackpyramid88 commented on GitHub (Feb 21, 2025):

@blackpyramid88 you should check whether they have been deleted from the filesystem, or just from ollama

The default location for models is something like C:\Users\AppData\Local\Ollama\models -- if they're gone from there you may be able to use a file recovery tool (e.g. PhotoRec), but I wouldn't pin my hopes on that. If they still exist in there you can probably re-add them (but I'm not familiar with how)

I got it! Just needed to run the ls command and load them back to Ollama

<!-- gh-comment-id:2675512889 --> @blackpyramid88 commented on GitHub (Feb 21, 2025): > [@blackpyramid88](https://github.com/blackpyramid88) you should check whether they have been deleted from the filesystem, or just from ollama > > The default location for models is something like _C:\Users<username>\AppData\Local\Ollama\models_ -- if they're gone from there you may be able to use a file recovery tool (e.g. PhotoRec), but I wouldn't pin my hopes on that. If they still exist in there you can probably re-add them (but I'm not familiar with how) I got it! Just needed to run the ls command and load them back to Ollama
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
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#805
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?