Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Voxtral-4B-TTS-2603-MLX-4bit – AI Model by redseaplume | AlphaNeural AI
You can deploy this model and start earning money today!
redseaplume
/
Voxtral-4B-TTS-2603-MLX-4bit
like
0
mlx
tts
voxtral
mistralai/Voxtral-4B-TTS-2603
finetune
cc-by-nc-4.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Voxtral 4B TTS, MLX 4-bit Quantized
4-bit quantized weights for
Voxtral 4B TTS
on Apple Silicon via MLX.
Backbone:
4-bit (group_size=64), ~2.6 GB (down from ~6.8 GB BF16)
Acoustic transformer:
BF16 (unchanged)
Vocoder:
BF16, pre-processed (weight-norm reconstructed, conv weights transposed, codebook precomputed)
Total file size: 3.4 GB (vs 7.5 GB BF16)
Usage
Requires the code from
redseaplume/Voxtral-4B-TTS-2603-MLX
. Point
model_path
at this repo.
What's in here
consolidated.safetensors
: all three components in one file
params.json
: model config
tekken.json
: tokenizer
voice_embedding/
: 20 pre-computed voice embeddings (.pt and .npz)
Notes
Only the backbone is quantized. Acoustic transformer and vocoder stay BF16.
Generation output differs slightly from BF16 (quantization is lossy). Frame counts may vary.
