RedHatAI
/

gemma-4-31B-it-NVFP4

Image-Text-to-Text

compressed-tensors

8-bit precision

Model card Files Files and versions

Resources

View closed (1)

Error KeyError: 'layers.0.experts.0.down_proj.input_global_scale' when running on vllm

#5 opened 2 days ago by

Running Gemma 4 Truthfully at 128K on One RTX 5090

#4 opened 5 days ago by

Please update tokenizer config as well

#2 opened 9 days ago by

Can you plese update the chat template

#1 opened 9 days ago by