KORMo-Web-11B

Try Try

KORMo-Web-11B has 11.2B parameters (10.2B active per token) and takes 22.4 GB on disk. See where its parameters live, layer by layer, and what hardware it needs.

At a glance

KORMo-VL/KORMo-Web-11B
Repo createdNov 14, 2026updated Nov 18, 2026
Model typeDenseFull attention (GQA)
InputsText + images434M vision encoder
Total parameters11.2B
Active per token10.2B92% of the model
ExpertsNone (dense)
Max context (from config)128K tokens
Layers40
On disk22.4 GB1 file
PrecisionBF16 (100%)
QuantizationNoneoriginal precision (BF16)
Fewest GPUs1× RTX 5090a single 32 GB card · weights only
FamilyFine-tune of KORMo-VL/KORMo-VL
Licenseapache-2.0
GitHubNot linked