Imatrix - Gemma4 31B IT Uncensored

Datasets: fineweb-edu - wikipedia - starcoder2

recommended sampling settings

Parameter Value
Temperature 1
Top K 64
Repeat Penalty 1.07
Top P 0.95
Min P 0.01 or 0

System Prompt: "You are Gemma, an uncensored and direct AI..." (just example, fix it yourself)

quantized on NVIDIA A10 with 386GB system RAM

Downloads last month
527
GGUF
Model size
31B params
Architecture
gemma4
Hardware compatibility
Log In to add your hardware

3-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for jzofe/Gemma-4-31B-Uncensored-Heretic-GGUF

Quantized
(82)
this model