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 #1703] Error: llama runner process has terminated. when running dolphin-mixtral #26722

New Issue
Closed
opened 2026-04-22 03:11:27 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-22 03:11:27 -05:00
Owner
Copy Link

Originally created by @G-only1 on GitHub (Dec 25, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1703

when i run ollama run dolphin-mixtral it gives the error Error: llama runner process has terminated.

Originally created by @G-only1 on GitHub (Dec 25, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1703 when i run ollama run dolphin-mixtral it gives the error Error: llama runner process has terminated.
GiteaMirror commented 2026-04-22 03:11:30 -05:00
Author
Owner
Copy Link

@ruucat commented on GitHub (Dec 26, 2023):

Same error with llava:latest

<!-- gh-comment-id:1869750959 --> @ruucat commented on GitHub (Dec 26, 2023): Same error with `llava:latest`
GiteaMirror commented 2026-04-22 03:11:30 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Dec 27, 2023):

It sounds like you may be running out of memory while loading the model.

Is there any more info in the logs you could share here?

https://github.com/jmorganca/ollama/blob/main/docs/troubleshooting.md

<!-- gh-comment-id:1870498404 --> @BruceMacD commented on GitHub (Dec 27, 2023): It sounds like you may be running out of memory while loading the model. Is there any more info in the logs you could share here? https://github.com/jmorganca/ollama/blob/main/docs/troubleshooting.md
GiteaMirror commented 2026-04-22 03:11:31 -05:00
Author
Owner
Copy Link

@jocot commented on GitHub (Dec 28, 2023):

I had the same error, I managed to fix it by setting the num_ctx parameter to 16384.

"The base model has 32k context, I finetuned it with 16k"
https://huggingface.co/TheBloke/dolphin-2.6-mixtral-8x7b-GGUF

Note: this problem also exists in the orca2:13b-q8_0 model, setting num_ctx to 8192 or 16384 gets it to work.

<!-- gh-comment-id:1871096175 --> @jocot commented on GitHub (Dec 28, 2023): I had the same error, I managed to fix it by setting the num_ctx parameter to 16384. "The base model has 32k context, I finetuned it with 16k" https://huggingface.co/TheBloke/dolphin-2.6-mixtral-8x7b-GGUF Note: this problem also exists in the orca2:13b-q8_0 model, setting num_ctx to 8192 or 16384 gets it to work.
GiteaMirror commented 2026-04-22 03:11:32 -05:00
Author
Owner
Copy Link

@williamsun-hha commented on GitHub (Dec 31, 2023):

@jocot Thank you very much for your help. Can you please share how do you do ( setting the num_ctx parameter to 16384.) in ollama, I do not see an option to set the parameter not in the command line option. Thank you very much for your help in advance!

<!-- gh-comment-id:1873054147 --> @williamsun-hha commented on GitHub (Dec 31, 2023): @jocot Thank you very much for your help. Can you please share how do you do ( setting the num_ctx parameter to 16384.) in ollama, I do not see an option to set the parameter not in the command line option. Thank you very much for your help in advance!
GiteaMirror commented 2026-04-22 03:11:33 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Jan 2, 2024):

@williamsun-hha
First make sure you're on a version of Ollama that supports the /set parameter option, the easiest way to do that is to make sure you're on latest:
https://github.com/jmorganca/ollama/blob/main/docs/faq.md#how-can-i-upgrade-ollama

Then run the set command like this:

ollama run dolphin-mixtral

>>> /set parameter num_ctx 16384
Set parameter 'num_ctx' to '16384'

... continue your session now with the context set
<!-- gh-comment-id:1873877704 --> @BruceMacD commented on GitHub (Jan 2, 2024): @williamsun-hha First make sure you're on a version of Ollama that supports the `/set parameter` option, the easiest way to do that is to make sure you're on latest: https://github.com/jmorganca/ollama/blob/main/docs/faq.md#how-can-i-upgrade-ollama Then run the set command like this: ``` ollama run dolphin-mixtral >>> /set parameter num_ctx 16384 Set parameter 'num_ctx' to '16384' ... continue your session now with the context set ```
GiteaMirror commented 2026-04-22 03:11:33 -05:00
Author
Owner
Copy Link

@vojtabohm commented on GitHub (Jan 2, 2024):

I have the same issue as well. I cannot run the set command since the run command fails before I get a chance to do anything else.

Running on M1 Max 32GB. Getting status 5, which means running out of memory.

warning: current allocated size is greater than the recommended max working set size 
ggml_metal_graph_compute: command buffer 4 failed with status 5

Is there a way I could limit the allocated memory? I would like to get it to run even if it's very slow to generate tokens.

<!-- gh-comment-id:1874642183 --> @vojtabohm commented on GitHub (Jan 2, 2024): I have the same issue as well. I cannot run the `set` command since the `run` command fails before I get a chance to do anything else. Running on M1 Max 32GB. Getting status 5, which means running out of memory. ``` warning: current allocated size is greater than the recommended max working set size ggml_metal_graph_compute: command buffer 4 failed with status 5 ``` Is there a way I could limit the allocated memory? I would like to get it to run even if it's very slow to generate tokens.
GiteaMirror commented 2026-04-22 03:11:34 -05:00
Author
Owner
Copy Link

@marko911 commented on GitHub (Jan 3, 2024):

I'm also on an M1 Pro 32GB and I get Error: ollama runner process has terminated when trying to run notux

<!-- gh-comment-id:1875087708 --> @marko911 commented on GitHub (Jan 3, 2024): I'm also on an M1 Pro 32GB and I get `Error: ollama runner process has terminated` when trying to run `notux`
GiteaMirror commented 2026-04-22 03:11:35 -05:00
Author
Owner
Copy Link

@G-only1 commented on GitHub (Jan 3, 2024):

It sounds like you may be running out of memory while loading the model.

Is there any more info in the logs you could share here?

https://github.com/jmorganca/ollama/blob/main/docs/troubleshooting.md

Dec 24 23:31:10 dolphin-virtual-machine systemd[1]: Started Ollama Service. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Your new public key is: Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFUoGHH4jz95Lzc1ptUUoARs1WXd319YwK54bLfxdX1v Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:737: total blobs: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:744: total unused blobs removed: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:895: Listening on 127.0.0.1:11434 (version 0.1.17) Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:915: warning: gpu support may not be enabled, check that you have installed GPU drivers: nvidia-smi command failed Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 200 | 129.465µs | 127.0.0.1 | HEAD "/" Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 404 | 358.46µs | 127.0.0.1 | POST "/api/show" Dec 24 23:31:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:33 download.go:123: downloading 122f07acc1ea in 64 413 MB part(s) Dec 24 23:41:31 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:31 download.go:123: downloading a47b02e00552 in 1 106 B part(s) Dec 24 23:41:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:33 download.go:123: downloading 9640c2212a51 in 1 41 B part(s) Dec 24 23:41:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:35 download.go:123: downloading 4b0d050e562d in 1 98 B part(s) Dec 24 23:41:38 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:38 download.go:123: downloading 4836176c502f in 1 484 B part(s) Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 13m30s | 127.0.0.1 | POST "/api/pull" Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 1.507254ms | 127.0.0.1 | POST "/api/show" Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:436: starting llama runner Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:494: waiting for llama runner to start responding Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:525: llama runner stopped successfully Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:04 | 500 | 2.189316673s | 127.0.0.1 | POST "/api/generate" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 37.038µs | 127.0.0.1 | HEAD "/" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 1.908081ms | 127.0.0.1 | GET "/api/tags" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 32.273µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 893.862µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 1.024683ms | 127.0.0.1 | POST "/api/show" Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:436: starting llama runner Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:525: llama runner stopped successfully Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:23 | 500 | 1.309327305s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 36.988µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 871.764µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 855.621µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:436: starting llama runner Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:525: llama runner stopped successfully Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:35 | 500 | 1.332430527s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:54 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:54 | 200 | 41.983µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 37.102µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 816.071µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 35.097µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 855.153µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 43.59µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 989.712µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 37.255µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 793.545µs | 127.0.0.1 | POST "/api/show" Dec 24 23:50:44 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:50:44 | 200 | 61.603µs | 127.0.0.1 | GET "/"Dec 24 23:31:10 dolphin-virtual-machine systemd[1]: Started Ollama Service. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Your new public key is: Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFUoGHH4jz95Lzc1ptUUoARs1WXd319YwK54bLfxdX1v Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:737: total blobs: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:744: total unused blobs removed: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:895: Listening on 127.0.0.1:11434 (version 0.1.17) Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:915: warning: gpu support may not be enabled, check that you have installed GPU drivers: nvidia-smi command failed Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 200 | 129.465µs | 127.0.0.1 | HEAD "/" Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 404 | 358.46µs | 127.0.0.1 | POST "/api/show" Dec 24 23:31:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:33 download.go:123: downloading 122f07acc1ea in 64 413 MB part(s) Dec 24 23:41:31 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:31 download.go:123: downloading a47b02e00552 in 1 106 B part(s) Dec 24 23:41:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:33 download.go:123: downloading 9640c2212a51 in 1 41 B part(s) Dec 24 23:41:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:35 download.go:123: downloading 4b0d050e562d in 1 98 B part(s) Dec 24 23:41:38 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:38 download.go:123: downloading 4836176c502f in 1 484 B part(s) Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 13m30s | 127.0.0.1 | POST "/api/pull" Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 1.507254ms | 127.0.0.1 | POST "/api/show" Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:436: starting llama runner Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:494: waiting for llama runner to start responding Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:525: llama runner stopped successfully Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:04 | 500 | 2.189316673s | 127.0.0.1 | POST "/api/generate" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 37.038µs | 127.0.0.1 | HEAD "/" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 1.908081ms | 127.0.0.1 | GET "/api/tags" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 32.273µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 893.862µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 1.024683ms | 127.0.0.1 | POST "/api/show" Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:436: starting llama runner Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:525: llama runner stopped successfully Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:23 | 500 | 1.309327305s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 36.988µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 871.764µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 855.621µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:436: starting llama runner Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:525: llama runner stopped successfully Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:35 | 500 | 1.332430527s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:54 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:54 | 200 | 41.983µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 37.102µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 816.071µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 35.097µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 855.153µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 43.59µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 989.712µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 37.255µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 793.545µs | 127.0.0.1 | POST "/api/show" Dec 24 23:50:44 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:50:44 | 200 | 61.603µs | 127.0.0.1 | GET "/"

<!-- gh-comment-id:1875395442 --> @G-only1 commented on GitHub (Jan 3, 2024): > It sounds like you may be running out of memory while loading the model. > > Is there any more info in the logs you could share here? > > https://github.com/jmorganca/ollama/blob/main/docs/troubleshooting.md `Dec 24 23:31:10 dolphin-virtual-machine systemd[1]: Started Ollama Service. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Your new public key is: Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFUoGHH4jz95Lzc1ptUUoARs1WXd319YwK54bLfxdX1v Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:737: total blobs: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:744: total unused blobs removed: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:895: Listening on 127.0.0.1:11434 (version 0.1.17) Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:915: warning: gpu support may not be enabled, check that you have installed GPU drivers: nvidia-smi command failed Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 200 | 129.465µs | 127.0.0.1 | HEAD "/" Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 404 | 358.46µs | 127.0.0.1 | POST "/api/show" Dec 24 23:31:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:33 download.go:123: downloading 122f07acc1ea in 64 413 MB part(s) Dec 24 23:41:31 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:31 download.go:123: downloading a47b02e00552 in 1 106 B part(s) Dec 24 23:41:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:33 download.go:123: downloading 9640c2212a51 in 1 41 B part(s) Dec 24 23:41:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:35 download.go:123: downloading 4b0d050e562d in 1 98 B part(s) Dec 24 23:41:38 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:38 download.go:123: downloading 4836176c502f in 1 484 B part(s) Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 13m30s | 127.0.0.1 | POST "/api/pull" Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 1.507254ms | 127.0.0.1 | POST "/api/show" Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:436: starting llama runner Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:494: waiting for llama runner to start responding Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:525: llama runner stopped successfully Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:04 | 500 | 2.189316673s | 127.0.0.1 | POST "/api/generate" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 37.038µs | 127.0.0.1 | HEAD "/" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 1.908081ms | 127.0.0.1 | GET "/api/tags" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 32.273µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 893.862µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 1.024683ms | 127.0.0.1 | POST "/api/show" Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:436: starting llama runner Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:525: llama runner stopped successfully Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:23 | 500 | 1.309327305s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 36.988µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 871.764µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 855.621µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:436: starting llama runner Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:525: llama runner stopped successfully Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:35 | 500 | 1.332430527s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:54 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:54 | 200 | 41.983µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 37.102µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 816.071µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 35.097µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 855.153µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 43.59µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 989.712µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 37.255µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 793.545µs | 127.0.0.1 | POST "/api/show" Dec 24 23:50:44 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:50:44 | 200 | 61.603µs | 127.0.0.1 | GET "/"Dec 24 23:31:10 dolphin-virtual-machine systemd[1]: Started Ollama Service. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: Your new public key is: Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFUoGHH4jz95Lzc1ptUUoARs1WXd319YwK54bLfxdX1v Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:737: total blobs: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 images.go:744: total unused blobs removed: 0 Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:895: Listening on 127.0.0.1:11434 (version 0.1.17) Dec 24 23:31:10 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:10 routes.go:915: warning: gpu support may not be enabled, check that you have installed GPU drivers: nvidia-smi command failed Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 200 | 129.465µs | 127.0.0.1 | HEAD "/" Dec 24 23:31:31 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:31:31 | 404 | 358.46µs | 127.0.0.1 | POST "/api/show" Dec 24 23:31:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:31:33 download.go:123: downloading 122f07acc1ea in 64 413 MB part(s) Dec 24 23:41:31 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:31 download.go:123: downloading a47b02e00552 in 1 106 B part(s) Dec 24 23:41:33 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:33 download.go:123: downloading 9640c2212a51 in 1 41 B part(s) Dec 24 23:41:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:35 download.go:123: downloading 4b0d050e562d in 1 98 B part(s) Dec 24 23:41:38 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:41:38 download.go:123: downloading 4836176c502f in 1 484 B part(s) Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 13m30s | 127.0.0.1 | POST "/api/pull" Dec 24 23:45:01 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:01 | 200 | 1.507254ms | 127.0.0.1 | POST "/api/show" Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:436: starting llama runner Dec 24 23:45:03 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:03 llama.go:494: waiting for llama runner to start responding Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:45:04 llama.go:525: llama runner stopped successfully Dec 24 23:45:04 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:45:04 | 500 | 2.189316673s | 127.0.0.1 | POST "/api/generate" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 37.038µs | 127.0.0.1 | HEAD "/" Dec 24 23:46:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:46:23 | 200 | 1.908081ms | 127.0.0.1 | GET "/api/tags" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 32.273µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 893.862µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:21 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:21 | 200 | 1.024683ms | 127.0.0.1 | POST "/api/show" Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:436: starting llama runner Dec 24 23:48:22 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:22 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:23 llama.go:525: llama runner stopped successfully Dec 24 23:48:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:23 | 500 | 1.309327305s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 36.988µs | 127.0.0.1 | HEAD "/" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 871.764µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:34 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:34 | 200 | 855.621µs | 127.0.0.1 | POST "/api/show" Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:403: skipping accelerated runner because num_gpu=0 Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:436: starting llama runner Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:494: waiting for llama runner to start responding Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:451: signal: illegal instruction (core dumped) Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:459: error starting llama runner: llama runner process has terminated Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: 2023/12/24 23:48:35 llama.go:525: llama runner stopped successfully Dec 24 23:48:35 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:35 | 500 | 1.332430527s | 127.0.0.1 | POST "/api/generate" Dec 24 23:48:54 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:48:54 | 200 | 41.983µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 37.102µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:14 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:14 | 200 | 816.071µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 35.097µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:23 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:23 | 200 | 855.153µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 43.59µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:39 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:39 | 200 | 989.712µs | 127.0.0.1 | POST "/api/show" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 37.255µs | 127.0.0.1 | HEAD "/" Dec 24 23:49:57 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:49:57 | 200 | 793.545µs | 127.0.0.1 | POST "/api/show" Dec 24 23:50:44 dolphin-virtual-machine ollama[3974]: [GIN] 2023/12/24 - 23:50:44 | 200 | 61.603µs | 127.0.0.1 | GET "/"`
GiteaMirror commented 2026-04-22 03:11:36 -05:00
Author
Owner
Copy Link

@jocot commented on GitHub (Jan 7, 2024):

I have the same issue as well. I cannot run the set command since the run command fails before I get a chance to do anything else.

Running on M1 Max 32GB. Getting status 5, which means running out of memory.

warning: current allocated size is greater than the recommended max working set size 
ggml_metal_graph_compute: command buffer 4 failed with status 5

Is there a way I could limit the allocated memory? I would like to get it to run even if it's very slow to generate tokens.

Yes you can adjust the num_ctx setting which involves editing a json configuration file.

I have the same issue as well. I cannot run the set command since the run command fails before I get a chance to do anything else.

Running on M1 Max 32GB. Getting status 5, which means running out of memory.

warning: current allocated size is greater than the recommended max working set size 
ggml_metal_graph_compute: command buffer 4 failed with status 5

Is there a way I could limit the allocated memory? I would like to get it to run even if it's very slow to generate tokens.

@vojtabohm @marko911

I've written a python script to edit the num_ctx setting (if you cannot start the model at all)

It should work on a Mac but I don't have a Mac to test it on.

Instructions are on the link:

https://gist.github.com/jocot/27fd0c6b370d5afd317b2a5602f4dea4

If it still won't run after changing num_ctx, then it's most likely due to insufficient RAM.

Let me know if any questions or issues.

I hope that helps!

<!-- gh-comment-id:1879904080 --> @jocot commented on GitHub (Jan 7, 2024): > I have the same issue as well. I cannot run the `set` command since the `run` command fails before I get a chance to do anything else. > > Running on M1 Max 32GB. Getting status 5, which means running out of memory. > > ``` > warning: current allocated size is greater than the recommended max working set size > ggml_metal_graph_compute: command buffer 4 failed with status 5 > ``` > > Is there a way I could limit the allocated memory? I would like to get it to run even if it's very slow to generate tokens. Yes you can adjust the num_ctx setting which involves editing a json configuration file. > I have the same issue as well. I cannot run the `set` command since the `run` command fails before I get a chance to do anything else. > > Running on M1 Max 32GB. Getting status 5, which means running out of memory. > > ``` > warning: current allocated size is greater than the recommended max working set size > ggml_metal_graph_compute: command buffer 4 failed with status 5 > ``` > > Is there a way I could limit the allocated memory? I would like to get it to run even if it's very slow to generate tokens. @vojtabohm @marko911 I've written a python script to edit the num_ctx setting (if you cannot start the model at all) It *should* work on a Mac but I don't have a Mac to test it on. Instructions are on the link: [https://gist.github.com/jocot/27fd0c6b370d5afd317b2a5602f4dea4](url) If it still won't run after changing num_ctx, then it's most likely due to insufficient RAM. Let me know if any questions or issues. I hope that helps!
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#26722
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?