ISTA-DASLab
/

gemma-3-27b-it-GPTQ-4b-128g

Image-Text-to-Text

text-generation-inference

compressed-tensors

Model card Files Files and versions Community

Resources

View closed (0)

Why is the model size of safetensor 5.23B parameters?

#6 opened about 2 months ago by

Can you share the GPTQ quantization code?

#5 opened 3 months ago by

Produce gibberish with dtype=auto

#4 opened 4 months ago by

QAT version

#3 opened 4 months ago by

vLLM on 24gb gpu

#2 opened 5 months ago by

Error

#1 opened 5 months ago by