Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
majentik
/
MERaLiON-2-10B-RotorQuant-MLX-2bit
like
0
Automatic Speech Recognition
MLX
5 languages
meralion2
meralion
speech
audio
speech-to-text
apple-silicon
quantized
2bit
rotorquant
gemma-2
whisper
sea-lion
custom_code
2-bit
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
MERaLiON-2-10B-RotorQuant-MLX-2bit
/
adaptor_config.json
majentik
Add MLX quantized model with KV cache compression
f87ab8d
verified
5 days ago
raw
Copy download link
history
blame
contribute
delete
Safe
82 Bytes
{
"speech_hidden_size"
:
1280
,
"text_hidden_size"
:
3584
,
"scale_factor"
:
15
}