Downloads · 30 days
3
3% of all-time downloads
Voxtral-4B-TTS-2603-MLX-4bit
mutableworlds/Voxtral-4B-TTS-2603-MLX-4bit
Voxtral-4B-TTS-2603-MLX-4bit is a machine learning model from mutableworlds. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as cc-by-nc-4.0.
4-bit quantized weights for Voxtral 4B TTS on Apple Silicon via MLX.
All-time downloads
90
Public
Repo size
3.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.7 GB · 99%
At a glance
- Library
- mlx
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Mar 30, 2026
- Updated
- Mar 30, 2026
- SHA
- 893aed43
Base models
Model card
From the Hugging Face model README
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 fileparams.json: model configtekken.json: tokenizervoice_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.
- Library
- mlx
- License
- cc-by-nc-4.0
- Created
- Mar 30, 2026
- Updated
- Mar 30, 2026