github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 05:36:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1348] deepseek-coder fails to run with error #26465

New Issue
Closed
opened 2026-04-22 02:45:53 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-22 02:45:53 -05:00
Owner
Copy Link

Originally created by @Huge on GitHub (Dec 1, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1348

ollama run deepseek-coder:6.7b-base-q3_K_S
Error: llama runner process has terminated
is worse than expected, I've supposed correct ggml/guff engine/library is bundled to the model in this packaging.

Originally created by @Huge on GitHub (Dec 1, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1348 ` ollama run deepseek-coder:6.7b-base-q3_K_S` `Error: llama runner process has terminated` is worse than expected, I've supposed correct ggml/guff engine/library is bundled to the model in this packaging.
GiteaMirror added the bug label 2026-04-22 02:45:53 -05:00
GiteaMirror commented 2026-04-22 02:45:54 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Dec 2, 2023):

Hi there, sorry this happened - may I ask what operating system you are on?

<!-- gh-comment-id:1836951130 --> @jmorganca commented on GitHub (Dec 2, 2023): Hi there, sorry this happened - may I ask what operating system you are on?
GiteaMirror commented 2026-04-22 02:45:55 -05:00
Author
Owner
Copy Link

@thawkins commented on GitHub (Dec 3, 2023):

Restarted a few times and then this issue disappeared for me, it may be that unlike other models deepseek requires a restart of the inference engine.

I'm on linux, ubuntu 23.10, i7 64GB ram, no GPU.

<!-- gh-comment-id:1837546831 --> @thawkins commented on GitHub (Dec 3, 2023): Restarted a few times and then this issue disappeared for me, it may be that unlike other models deepseek requires a restart of the inference engine. I'm on linux, ubuntu 23.10, i7 64GB ram, no GPU.
GiteaMirror commented 2026-04-22 02:45:55 -05:00
Author
Owner
Copy Link

@RussellCanfield commented on GitHub (Dec 8, 2023):

I get a similar error:

'{"error":"model 'deepseek-coder' not found, try pulling it first"}'

mode: deepseek-coder:6.7b-base-q4_0
platform: macOS m1

<!-- gh-comment-id:1847841283 --> @RussellCanfield commented on GitHub (Dec 8, 2023): I get a similar error: '{"error":"model 'deepseek-coder' not found, try pulling it first"}' mode: deepseek-coder:6.7b-base-q4_0 platform: macOS m1
GiteaMirror commented 2026-04-22 02:45:56 -05:00
Author
Owner
Copy Link

@iDevEngineer commented on GitHub (Feb 6, 2024):

Has this been resolved as I'm having the same error too, using VSCode Insider?
platform: macOS m1

<!-- gh-comment-id:1928722963 --> @iDevEngineer commented on GitHub (Feb 6, 2024): Has this been resolved as I'm having the same error too, using VSCode Insider? platform: macOS m1
GiteaMirror commented 2026-04-22 02:45:56 -05:00
Author
Owner
Copy Link

@hasib-devs commented on GitHub (Feb 6, 2024):

It is still happening on vscode insiders with cody extension.
platform: macOS Intel

<!-- gh-comment-id:1928882250 --> @hasib-devs commented on GitHub (Feb 6, 2024): It is still happening on vscode insiders with cody extension. platform: macOS Intel
GiteaMirror commented 2026-04-22 02:45:57 -05:00
Author
Owner
Copy Link

@macius702 commented on GitHub (Feb 19, 2024):

In my settings.json I replaced

    "cody.autocomplete.experimental.ollamaOptions": {
        

        "url": "http://localhost:11434",
        "model": "deepseek-coder:6.7b-base-q4_K_M",
    }
    

}

with

    "cody.autocomplete.experimental.ollamaOptions": {
        

        "url": "http://localhost:11434",
        "model": "codellama:7b-code"
    }
    

}

which helped.

<!-- gh-comment-id:1951856902 --> @macius702 commented on GitHub (Feb 19, 2024): In my settings.json I replaced ``` "cody.autocomplete.experimental.ollamaOptions": { "url": "http://localhost:11434", "model": "deepseek-coder:6.7b-base-q4_K_M", } } ``` with ``` "cody.autocomplete.experimental.ollamaOptions": { "url": "http://localhost:11434", "model": "codellama:7b-code" } } ``` which helped.
GiteaMirror commented 2026-04-22 02:45:57 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 20, 2024):

Is this still an issue? Please let me know and I can re-open the issue. Thanks so much!

<!-- gh-comment-id:1953344588 --> @jmorganca commented on GitHub (Feb 20, 2024): Is this still an issue? Please let me know and I can re-open the issue. Thanks so much!
GiteaMirror commented 2026-04-22 02:45:57 -05:00
Author
Owner
Copy Link

@peterturquoise commented on GitHub (Apr 21, 2024):

Still happening for me, same issues with codellama and deepseek-code, but fine with mistral 🤷 ?? Obvs they are pulled....

Error:
litellm.exceptions.APIConnectionError: {"error":"model 'deepseek-coder' not found, try pulling it first"}

Config of models:
config_list_mistral_local = [
{
"model":"ollama/mistral",
"base_url": "http://0.0.0.0:4000",
"api_key": "NULL"
}
]

config_list_codellama_local = [
{
"model":"ollama/codellama",
"base_url": "http://0.0.0.0:46967",
"api_key": "NULL"
}
]

config_list_deepseek_coder_local = [
{
"model":"ollama/deepseek-coder",
"base_url": "http://0.0.0.0:2409",
"api_key": "NULL"
}
]

llm_config_mistral = {
"config_list": config_list_mistral_local
}

llm_config_codellama = {
"config_list": config_list_codellama_local
}

llm_config_deepseek_coder = {
"config_list": config_list_deepseek_coder_local
}

<!-- gh-comment-id:2068209624 --> @peterturquoise commented on GitHub (Apr 21, 2024): Still happening for me, same issues with codellama and deepseek-code, but fine with mistral :shrug: ?? Obvs they are pulled.... Error: litellm.exceptions.APIConnectionError: {"error":"model 'deepseek-coder' not found, try pulling it first"} Config of models: config_list_mistral_local = [ { "model":"ollama/mistral", "base_url": "http://0.0.0.0:4000", "api_key": "NULL" } ] config_list_codellama_local = [ { "model":"ollama/codellama", "base_url": "http://0.0.0.0:46967", "api_key": "NULL" } ] config_list_deepseek_coder_local = [ { "model":"ollama/deepseek-coder", "base_url": "http://0.0.0.0:2409", "api_key": "NULL" } ] llm_config_mistral = { "config_list": config_list_mistral_local } llm_config_codellama = { "config_list": config_list_codellama_local } llm_config_deepseek_coder = { "config_list": config_list_deepseek_coder_local }
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#26465
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?