Hugging Face's logo

lmstudio-community
/
gemma-3n-E4B-it-MLX-4bit

Image-Text-to-Text
Transformers
Safetensors
MLX
gemma3n
automatic-speech-recognition
automatic-speech-translation
audio-text-to-text
video-text-to-text
conversational
4-bit precision
Model card Files
xet
Community
1

Why safetensors are duplicated?

#1
by olegshulyakov - opened
Discussion
olegshulyakov

@lmmy why model.safetensors are duplicated twice? 4 bit model should be about 4-4,5GB like GGUF does.

will-lms
 LM Studio Community org

Removed!

will-lms changed discussion status to closed

Sign up or log in to comment