Hugging Face's logo

majentik
/
MERaLiON-2-3B-RotorQuant-MLX-4bit

Automatic Speech Recognition
MLX
meralion2
meralion
speech
audio
speech-to-text
apple-silicon
quantized
4bit
rotorquant
gemma-2
whisper
sea-lion
custom_code
Model card Files
xet
 Community
MERaLiON-2-3B-RotorQuant-MLX-4bit / generation_config.json

Commit History

Add MLX quantized model with KV cache compression
1785a33
verified

majentik commited on