what variant? I’d considered DeepSeek far too large for any consumer GPUs | Hacker News

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

		gcr 7 months ago \| parent \| context \| favorite \| on: Gemma 3 QAT Models: Bringing AI to Consumer GPUs what variant? I’d considered DeepSeek far too large for any consumer GPUs

scosman 7 months ago [–]

Some people run Deepseek on CPU. 37B active params - it isn't fast but it's passible.

danielbln 7 months ago | [–]

Actual deepseek or some qwen/llama reasoning fine-tune?

scosman 7 months ago | | [–]

Actual Deepseek. 500gb of memory and a threadripper works. Not a standard PC spec, but a common ish home brew setup for single user Deepseek.

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