Drilldown: Recipe
More actions
Recipe > quant:
W4A16 (INT4 weights, Marlin kernels) 
& source:
https://github.com/vektorprime/qwen38-flash-next-pp2
& source:
https://github.com/vektorprime/qwen38-flash-next-pp2 Use the filters below to narrow your results.
page:
(There are no values for this filter)
model:
(There are no values for this filter)
quant: (Click arrow to add another value)
engine:
(There are no values for this filter)
engine version:
(There are no values for this filter)
cards:
(There are no values for this filter)
card count:
(There are no values for this filter)
topology:
(There are no values for this filter)
context:
(There are no values for this filter)
decode tps:
(There are no values for this filter)
prefill tps:
(There are no values for this filter)
vram per card:
(There are no values for this filter)
power cap:
(There are no values for this filter)
driver:
(There are no values for this filter)
unlock build:
(There are no values for this filter)
status:
(There are no values for this filter)
tested by:
(There are no values for this filter)
tested on:
(There are no values for this filter)
source: (Click arrow to add another value)
There are no results for this report.