Viewing profile — ak_t

It doesn't need extra quantization. The official weights are natively mixed precision FP4/FP8, so it fits in ~160GB. The API slowness is probably from being batched with other conc…

Note this is the 07/31 release of DSv4 flash and not the "preview" that they put out a couple months or so ago. I've been running this model locally for a week, and the preview ver…

I haven't live there since 2020, but before that it was all various SaaS and data pipeline related billboards.

It's expensive to run it locally at full quality, but at least on my setup, its about 5 times faster than any API, and is completely private.