Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
google
/
gemma-3-27b-it
like
1.64k
Follow
Google
32.9k
Image-Text-to-Text
Transformers
Safetensors
gemma3
conversational
text-generation-inference
arxiv:
28 papers
License:
gemma
Model card
Files
Files and versions
xet
Community
91
Train
Deploy
Use this model
CUDA out of memory issue when deploying on vllm, how to solve
#80
by
elstoneng
- opened
Jul 3
Discussion
elstoneng
Jul 3
This comment has been hidden (marked as Resolved)
elstoneng
changed discussion title from
CUDA out of memory issue, how to solve
to
CUDA out of memory issue when deploying on vllm, how to solve
Jul 3
elstoneng
changed discussion status to
closed
Jul 3
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Comment
·
Sign up
or
log in
to comment
