new | ask | show | jobs
petu 4 hours ago  [ - ]

V4 Flash also was released as mostly FP4, but this one is FP8 (?). 160GB vs 510GB.

Original Flash good fit for dual Spark / Strix Halo machines. This one would require third party quants and even then 4 machines.

Edit: Most of added weights/size are Engrams?

> Overall, DeepSeek-V4.1-Flash has 552B backbone parameters and 196B Engram parameters, activating 8B parameters per token during prefill and 16B during decode.

Those can stay on SSD. So I guess / it possible, that non-engram portion is still FP4 of ~same size! Need to read tech report.

petu 3 hours ago  [ - ]

It's larger than previous V4 Flash.

  552B in ~FP4, 306GB.   
  196B of FP8 Engrams, another 204GB, not necessary to keep in RAM.  
  KV cache sees another 4x size reduction, just 900MB for 1M.
So 384GB needed for a chance of achieving useful speeds. Three Sparks or quad RTX PRO 6000.
npodbielski 2 hours ago  [ - ]

Or two gorgon halos?