Check out the GLM models, they are excellent | Hacker News

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

		OGEnthusiast 14 days ago \| parent \| context \| favorite \| on: Qwen3-Max-Thinking Check out the GLM models, they are excellent

khimaros 14 days ago [–]

Minimax m2.1 rivals GLM 4.7 and fits in 128GB with 100k context at 3bit quantization.

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