Skip to content
Constructor
My neuronets
Registry
Spaces
Docs
FAQ
EN
▾
Testnet
▾
Sign in
Models
/
nemotron-3-super-120b
⧉
N
Nemotron-3 Super 120B-A12B
NVIDIA · Nemotron-3
Create a neuronet with this model →
LLM
NVIDIA-Open-Model
public
Trusted
120B params
moe
Super 120B-A12B: single 80 GB card at 4-bit.
Model card
Spec & files
Deploy settings
Super 120B-A12B: single 80 GB card at 4-bit.
At a glance
Task:
LLM (InferenceV1)
Params:
120B
License:
NVIDIA-Open-Model (commercial use OK)
Hardware:
272 GB+ VRAM
dtype:
Bf16, Fp16