Pick a decent quant (4-6KM) then use llama-fit-params and try it yourself to see... | Hacker News

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

		tommy_axle 31 days ago \| parent \| context \| favorite \| on: Qwen3.6-35B-A3B: Agentic coding power, now open to... Pick a decent quant (4-6KM) then use llama-fit-params and try it yourself to see if it's giving you what you need.

gunalx 31 days ago [–]

I habe found llama-fit sometimes just selects a way to conservative load with VRAM to spare.

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