Downloads · 30 days
20
32% of all-time downloads
parakeet-tdt-0.6b-v2-bf16
Reesthebeast/parakeet-tdt-0.6b-v2-bf16
parakeet-tdt-0.6b-v2-bf16 is a automatic speech recognition model from Reesthebeast. Use it when you need speech turned into text. It is set up for parakeet-mlx. The card lists the license as cc-by-4.0.
mlx-community/parakeet-tdt-0.6b-v2 with the weights stored as bfloat16 instead of float32. Nothing else differs — same architecture, same tokenizer, same values.
All-time downloads
62
Public
Parameters
618M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- parakeet-mlx
- License
- cc-by-4.0
- Access
- Public
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026
- SHA
- 0b96b79e
Base models
Model card
From the Hugging Face model README
Reesthebeast/parakeet-tdt-0.6b-v2-bf16
mlx-community/parakeet-tdt-0.6b-v2 with the weights stored as bfloat16 instead of float32. Nothing else differs — same architecture, same tokenizer, same values.
Why
parakeet_mlx.from_pretrained loads with dtype=mx.bfloat16 by default, so the
published float32 weights are narrowed to bfloat16 the moment they are read.
Storing them that way makes the download 2.47 GB → 1.24 GB
with no effect on output: every tensor here is bit-identical to what the float32
repo becomes once loaded.
Verified by transcribing the same audio through both and comparing the text character for character.
Use
from parakeet_mlx import from_pretrained
model = from_pretrained("Reesthebeast/parakeet-tdt-0.6b-v2-bf16")
Built for LocalFlow, a fully-local push-to-talk dictation app for macOS, where this halves a new user's first-run download.
- Task
- Automatic Speech Recognition
- Library
- parakeet-mlx
- License
- cc-by-4.0
- Languages
- en
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026