Those sound like the sort of issues which could be caused by your server silentl... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		whbrown on March 12, 2025 \| parent \| context \| favorite \| on: Gemma3 – The current strongest model that fits on ... Those sound like the sort of issues which could be caused by your server silently truncating the middle of your prompts. By default, Ollama uses a context window size of 2048 tokens.

tarruda on March 12, 2025 [–]

I checked this, the whole conversation was about 1000 tokens.

I suspect the Ollama version might have wrong default settings, such as conversation delimiters. The experience of Gemma 3 in AI studio is completely different.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact