Drilldown: Recipe
More actions
Recipe > model:
GLM-5.3-Flash (320B MoE, 18B active) 
& engine:
Morrowmake/vllm-cmp170hx (vLLM fork, container image)
& cards:
8 GB
& engine:
Morrowmake/vllm-cmp170hx (vLLM fork, container image)
& cards:
8 GB Use the filters below to narrow your results.
model: (Click arrow to add another value)
quant:
engine: (Click arrow to add another value)
engine version:
cards: (Click arrow to add another value)
card count:
topology:
context:
decode tps:
prefill tps:
vram per card:
power cap:
status:
tested by:
tested on:
Showing below up to 1 result in range #1 to #1.