The 26B model is really surprising, and it is impressively concise — it spends a... | Hacker News

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

dofm 29 days ago | parent | context | favorite | on: Gemma 4 QAT models: Optimizing compression for mob...

The 26B model is really surprising, and it is impressively concise — it spends a lot less time dithering than Qwen3.6.

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