[GH-ISSUE #521] Download models #414

New issue

Closed

opened 2026-10-26 21:20:57 +00:00 by bsakaguchi · 5 comments

bsakaguchi commented

2026-10-26 21:20:57 +00:00

Owner

Originally created by @mou7664 on GitHub (Mar 2, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/521

Hello,

I tried searching online for a 1.5B model (as I do not have enough computer resources) for ollama without success?
My computer currently runs under Linux.
Would you please be able to provide a link/page to download the open-source model.

Thank you,

Originally created by @mou7664 on GitHub (Mar 2, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/521 Hello, I tried searching online for a 1.5B model (as I do not have enough computer resources) for ollama without success? My computer currently runs under Linux. Would you please be able to provide a link/page to download the open-source model. Thank you,

bsakaguchi

2026-10-26 21:20:57 +00:00

closed this issue
added the
stale

closed-as-stale
labels

bsakaguchi commented

2026-10-26 21:20:58 +00:00

Author

Owner

@novacx0222 commented on GitHub (Mar 2, 2025):

The DeepSeek models are quite large and require substantial computing resources to run. However, you may consider using the distilled version (1.5B), which is more lightweight. You can find it here. Additionally, the link to the safetensors file is available at this page.

@novacx0222 commented on GitHub (Mar 2, 2025): The DeepSeek models are quite large and require substantial computing resources to run. However, you may consider using the distilled version (1.5B), which is more lightweight. You can find it [here](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B). Additionally, the link to the safetensors file is available at [this page](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/tree/main).

bsakaguchi commented

2026-10-26 21:20:58 +00:00

Author

Owner

@novacx0222 commented on GitHub (Mar 2, 2025):

If you're using llama.cpp or Ollama on Linux, you can take advantage of the quantized model, which offers lower precision and a smaller size. You can find it here.

For guidance on using GGUF files with Ollama, please refer to the official documentation: Hugging Face Ollama Guide.

@novacx0222 commented on GitHub (Mar 2, 2025): If you're using **llama.cpp** or **Ollama** on Linux, you can take advantage of the **quantized model**, which offers lower precision and a smaller size. You can find it [here](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF). For guidance on using GGUF files with Ollama, please refer to the official documentation: [Hugging Face Ollama Guide](https://huggingface.co/docs/hub/ollama).

bsakaguchi commented

2026-10-26 21:20:58 +00:00

Author

Owner

@mou7664 commented on GitHub (Mar 4, 2025):

For clarification, what are the system requirements for superior models

@mou7664 commented on GitHub (Mar 4, 2025): For clarification, what are the system requirements for superior models

bsakaguchi commented

2026-10-26 21:20:59 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Apr 18, 2025):

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

@github-actions[bot] commented on GitHub (Apr 18, 2025): This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

bsakaguchi commented

2026-10-26 21:20:59 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (May 22, 2025):

false

@github-actions[bot] commented on GitHub (May 22, 2025): false

bsakaguchi referenced this issue

2026-10-26 21:26:46 +00:00

[PR #414] [CLOSED] docs: update README.md #789