This has been my experience as well. I don’t use system prompts anymore. Curious if there’s a good reason to start.

It matters as a common standard for model integration. System messages aren't removed when regular context messages start to get cut, the model pays more attention to tools and other directives defined there. Like situational context, language it should use, type of responses, etc. OAI/Anthropic give their models system prompts a mile long to tune their behaviour to a T.

There's also the ideological camp with Hartford and Nous and the rest where models are supposed to be trained as generally as possible, with the system prompt being strictly followed to adapt it to specific use cases.

Direct prompt injection attacks can be somewhat mitigated by using system prompts (though not completely) if that helps.

I've read the Gemma 3 technical report, it doesn't mention anything about it in the format section. Did they forget to include that? Where did you find the source that claims otherwise?

Google AI Studio offers no system prompt option for Gemma 3 which also suggests this model doesn't support it...

The official ggufs have this in them as an example, I'm even more confused now:

<start_of_turn>user

You are a helpful assistant

Hello<end_of_turn>

<start_of_turn>model

Hi there<end_of_turn>

<start_of_turn>user

How are you?<end_of_turn>

<start_of_turn>model

I was confused by this too, but now I think they’re just suggesting to prepend the system prompt to the first user prompt.

I think the ggufs took the chat template defined in tokenizer_config.json , which basically does that.

My bad, original comment updated.