[semicolon_storm]

Are you referring to the distilled models?

[whimsicalism]

yes, they are not r1

[BeefySwain]

Can you explain what you mean by this?

[baobabKoodaa]

For example, the model named "deepseek-r1:8b" by ollama is not a deepseek r1 model. It is actually a fine tune of Meta's Llama 8b, fine tuned on data generated by deepseek r1.