Downloads · 30 days
11
10% of all-time downloads
parakeet-tdt-0.6b-v2-int4
sonic-speech/parakeet-tdt-0.6b-v2-int4
parakeet-tdt-0.6b-v2-int4 is a automatic speech recognition model from sonic-speech. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as cc-by-4.0.
Mixed-precision variant: encoder quantized to INT4, decoder + joint network remain BF16. Optimized for Apple Silicon with reduced memory footprint.
All-time downloads
115
Public
Parameters
618M
470 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors470 MB · 100%
Parameter types
How the weights are stored.
U32533M · 86%
Base models
Model card
From the Hugging Face model README
Parakeet TDT 0.6B V2 (MLX, Encoder INT4)
Mixed-precision variant: encoder quantized to INT4, decoder + joint network remain BF16. Optimized for Apple Silicon with reduced memory footprint.
| Metric | BF16 Reference | This (INT4) |
|---|---|---|
| Peak memory | ~3GB | ~1.0GB |
| Weight size | ~1.2GB | ~330MB |
| WER impact | baseline | +0.3-0.5% expected |
Usage
from parakeet import from_pretrained
model = from_pretrained("sonic-speech/parakeet-tdt-0.6b-v2-int4")
result = model.transcribe("audio.wav")
Quantization Details
- Encoder: INT4, group_size=64
- Decoder (PredictNetwork): BF16 (accuracy-critical)
- Joint network: BF16 (accuracy-critical)
- Method: Post-training quantization via
mlx.nn.quantize - Source:
sonic-speech/parakeet-tdt-0.6b-v2
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- cc-by-4.0
- Languages
- en
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026