On: DeepSeek-v4.1-Flash-1017

Forgive the ignorance, but how are you running a 763B parameter model on 64GB of RAM?

SSD weights streaming. The actual weights is 552B, then engram.

which engine?

https://releases.drawthings.ai/p/public-beta-of-local-code-b...

By “quantitizing” it

The smallest quant is still over 100GB, so I don't know how that fits in 64GB RAM. It would have to be partly streamed from disk.