parakeet-tdt-0.6b-v3
This model was converted to MLX format from nvidia/parakeet-tdt-0.6b-v3 using the conversion script. Please refer to original model card for more details on the model.
Params
630 M
Context
—
Downloads 30d
2.7 M
Likes
72
Download history
daily snapshots · 106 days
▲ 433 K in the last 30 days (19.1%)
2.8 M2.3 M
Oct 12Oct 22Nov 1Nov 10
2.8 M1.3 M
Aug 13Sep 12Oct 12Nov 10
2.8 M1.3 M
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 2.5 GB | 3.4 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 630 M
- Tensor type
- F32
- Licence
- cc-by-4.0
- First seen on the Hub
- 2025-08-16
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any automatic-speech-recognition model