Skip to content
Constructor
My neuronets
Registry
Spaces
Docs
FAQ
EN
▾
Testnet
▾
Sign in
Models
/
gemma-4-31b-fp8
⧉
G
Gemma 4 31B (FP8-block)
Google · Gemma 4
Create a neuronet with this model →
LLM
Gemma-Terms
public
Trusted
31B params
chat
flagship
fp8
quantized
Ready-made FP8-block build of Gemma 4 31B.
Model card
Spec & files
Deploy settings
Ready-made FP8-block build of Gemma 4 31B.
At a glance
Task:
LLM (InferenceV1)
Params:
31B
License:
Gemma-Terms (commercial use OK)
Hardware:
37 GB+ VRAM
dtype:
Fp8
