unsloth
/

gemma-3-27b-it-unsloth-bnb-4bit

text-generation-inference

4-bit precision

Model card Files Files and versions

Resources

View closed (1)

可否进一步创建mlx支持版本？【Could you please create a version that supports mlx as well?】

#5 opened 7 months ago by

significant extra memory usage compared to the other 27b

#4 opened 7 months ago by

Is it possible to fine-tune gemma 3 in a context beyond 131k?

#3 opened 8 months ago by

fp16 merge from this model checkpoint

#1 opened 9 months ago by