Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
majentik
/
MERaLiON-3-10B-RotorQuant-MLX-8bit
like
0
Automatic Speech Recognition
MLX
meralion3
rotorquant
kv-cache-quantization
meralion
speech-to-text
multimodal
audio
quantized
8bit
apple-silicon
custom_code
arxiv:
2504.19874
License:
other
Model card
Files
Files and versions
xet
Community
Use this model
main
MERaLiON-3-10B-RotorQuant-MLX-8bit
12.1 GB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
majentik
Re-upload with properly quantized decoder (encoder/adaptor bf16)
f818655
verified
about 14 hours ago
.gitattributes
1.63 kB
Add MLX quantized model with KV cache compression
2 days ago
README.md
3.68 kB
Add MLX quantized model with KV cache compression
2 days ago
adaptor.safetensors
128 MB
xet
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
adaptor_config.json
170 Bytes
Add MLX quantized model with KV cache compression
2 days ago
config.json
3.06 kB
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
decoder-00000.safetensors
3.1 GB
xet
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
decoder-00001.safetensors
2.28 GB
xet
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
decoder-00002.safetensors
2.25 GB
xet
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
decoder-00003.safetensors
2.26 GB
xet
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
decoder-00004.safetensors
788 MB
xet
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
decoder.safetensors.index.json
79.4 kB
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
decoder_config.json
1.04 kB
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
encoder.safetensors
1.27 GB
xet
Re-upload with properly quantized decoder (encoder/adaptor bf16)
about 14 hours ago
encoder_config.json
1.25 kB
Add MLX quantized model with KV cache compression
2 days ago
generation_config.json
Safe
170 Bytes
Add MLX quantized model with KV cache compression
2 days ago
preprocessor_config.json
Safe
443 Bytes
Add MLX quantized model with KV cache compression
2 days ago
processor_config.json
Safe
281 Bytes
Add MLX quantized model with KV cache compression
2 days ago
special_tokens_map.json
Safe
530 Bytes
Add MLX quantized model with KV cache compression
2 days ago
tokenizer.json
Safe
34.4 MB
xet
Add MLX quantized model with KV cache compression
2 days ago
tokenizer.model
Safe
4.24 MB
xet
Add MLX quantized model with KV cache compression
2 days ago
tokenizer_config.json
Safe
46.9 kB
Add MLX quantized model with KV cache compression
2 days ago