Is this something that will show up in Ollama any time soon to increase context ... | Hacker News

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

		chr15m 58 days ago \| parent \| context \| favorite \| on: What if AI doesn't need more RAM but better math? Is this something that will show up in Ollama any time soon to increase context size of local models?

zozbot234 58 days ago [–]

KV quantization has long been available in llama.cpp

chr15m 58 days ago | [–]

Yes but the optimisation described has not right?

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