I will, right now. EDIT: opencode was a bit slow with qwen3.5:35b using Ollama. ... | Hacker News

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

		mark_l_watson 2 days ago \| parent \| context \| favorite \| on: Qwen3.5 122B and 35B models offer Sonnet 4.5 perfo... I will, right now. EDIT: opencode was a bit slow with qwen3.5:35b using Ollama. Faster/nicer to use with Liquid lfm2:latest

		help

johnnyApplePRNG 2 days ago [–]

Try llama.cpp - it usually excels with these MoE models imho.

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