[GH-ISSUE #12269] Individual small model models have been failing to import #8158

Open
opened 2026-04-12 20:33:36 -05:00 by GiteaMirror · 6 comments
Owner

Originally created by @STARS7yao on GitHub (Sep 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12269

What is the issue?

I ran this command: "ollama create DeepSeek-1.5B-Q8_0 -f H: large model \llm_model\DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt", but there was no movement at all, only in task management, it kept reading the file. This model is only 1.76GB in size.

Image Image Image

Relevant log output


OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @STARS7yao on GitHub (Sep 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12269 ### What is the issue? I ran this command: "ollama create DeepSeek-1.5B-Q8_0 -f H: large model \llm_model\DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt", but there was no movement at all, only in task management, it kept reading the file. This model is only 1.76GB in size. <img width="960" height="104" alt="Image" src="https://github.com/user-attachments/assets/4235b2fa-1d08-4ad6-a609-5dbabf8ef496" /> <img width="1078" height="889" alt="Image" src="https://github.com/user-attachments/assets/449dc9fd-f3eb-4023-bb21-4d802b6c39c0" /> <img width="421" height="651" alt="Image" src="https://github.com/user-attachments/assets/af85b313-ad74-4f95-8a4a-8e0d02497d73" /> ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 20:33:36 -05:00
Author
Owner

@rick-github commented on GitHub (Sep 12, 2025):

Contents of DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt?

<!-- gh-comment-id:3285796607 --> @rick-github commented on GitHub (Sep 12, 2025): Contents of `DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt`?
Author
Owner

@STARS7yao commented on GitHub (Sep 12, 2025):

Contents of DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt?  的内容 DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt
It is a path for model import.
Image

<!-- gh-comment-id:3285811146 --> @STARS7yao commented on GitHub (Sep 12, 2025): > Contents of `DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt`?  的内容 `DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt` ? It is a path for model import. <img width="626" height="637" alt="Image" src="https://github.com/user-attachments/assets/25768165-d989-4d6f-9b40-bea2fe539f68" />
Author
Owner

@STARS7yao commented on GitHub (Sep 12, 2025):

Contents of DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt?  的内容 DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt
This model was downloaded from Modelscope, I tried to download another one again, from the official website of Ollama

<!-- gh-comment-id:3285825937 --> @STARS7yao commented on GitHub (Sep 12, 2025): > Contents of `DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt`?  的内容 `DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.txt` ? This model was downloaded from Modelscope, I tried to download another one again, from the official website of Ollama
Author
Owner

@rick-github commented on GitHub (Sep 12, 2025):

Please don't post screenshots of text files.

Where did the GGUF come from?

<!-- gh-comment-id:3285839071 --> @rick-github commented on GitHub (Sep 12, 2025): Please don't post screenshots of text files. Where did the GGUF come from?
Author
Owner

@STARS7yao commented on GitHub (Sep 12, 2025):

Please don't post screenshots of text files.请不要发布文本文件的屏幕截图。

Where did the GGUF come from?GGUF 从何而来?
Downloaded from this website community:
https://www.modelscope.cn/models/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/files

<!-- gh-comment-id:3285873280 --> @STARS7yao commented on GitHub (Sep 12, 2025): > Please don't post screenshots of text files.请不要发布文本文件的屏幕截图。 > > Where did the GGUF come from?GGUF 从何而来? Downloaded from this website community: https://www.modelscope.cn/models/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/files
Author
Owner

@STARS7yao commented on GitHub (Sep 12, 2025):

I just tried this command to work: "ollama run modelscope.cn/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF", maybe I download this model and import it manually, but I also need to adapt the corresponding modelfile

<!-- gh-comment-id:3285885894 --> @STARS7yao commented on GitHub (Sep 12, 2025): I just tried this command to work: "ollama run modelscope.cn/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF", maybe I download this model and import it manually, but I also need to adapt the corresponding modelfile
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8158