[ipsum2]

Title is wrong, only the distilled models from llama, qwen are on ollama, not the actual official MoE r1 model from deepseekv3.

[mchiang]

Sorry about that. We are currently uploading the 671B MoE R1 model as well. We needed some extra time to validate it on Ollama.

[ipsum2]

The naming of the models is quite confusing too...

[mchiang]

Did you mean the tags or the specific names from the distilled models?

[mchiang]

the 671B model is now available:

4 bit quantized: ollama run deepseek-r1:671b

(400GB+ VRAM/Unified memory required to run this)

https://ollama.com/library/deepseek-r1/tags

8 bit quantization still being uploaded