majentik
/

MERaLiON-3-10B-RotorQuant-MLX-4bit

Automatic Speech Recognition

kv-cache-quantization

Model card Files Files and versions

MERaLiON-3-10B-RotorQuant-MLX-4bit / decoder_config.json

Commit History

Re-upload with properly quantized decoder (encoder/adaptor bf16)

7f1bc8b
verified

majentik commited on about 13 hours ago

Add MLX quantized model with KV cache compression

918e195
verified

majentik commited on 2 days ago