Download models

[project21212]

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,

[cx0222]

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.

[cx0222]

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.