Store › model › Speech
parakeet-tdt-0.6b-v3-gguf
by handy-computer · source Hugging Face · updated 2026-09-15
cc-by-4.0463 MB~2 GB RAMsource aliveunlabeled
parakeet-tdt-0.6b-v3: transcribe.cpp GGUF
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:handy-computer/parakeet-tdt-0.6b-v3-gguf and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v3-gguf
- License: cc-by-4.0
- Requirements: about 2 GB of RAM, 463 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with whisper.cpp.
- Tags:
transcribe.cppggufasrspeech-to-textparakeetconformerrnnttdtmultilingualautomatic-speech-recognitionbghrcsdanlen
Numbers
- 575,793 downloads on Hugging Face
- 6 likes
- license cc-by-4.0
- 0.5 GB for parakeet-tdt-0.6b-v3-Q4_K_M.gguf
Numbers as of 2026-10-02 20:59 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
parakeet-tdt-0.6b-v3-F16.gguf | F16 | 1.2 GB |
parakeet-tdt-0.6b-v3-F32.gguf | F32 | 2.3 GB |
parakeet-tdt-0.6b-v3-Q4_K_M.gguf | Q4_K_M | 463 MB |
parakeet-tdt-0.6b-v3-Q5_K_M.gguf | Q5_K_M | 524 MB |
parakeet-tdt-0.6b-v3-Q6_K.gguf | Q6_K | 582 MB |
parakeet-tdt-0.6b-v3-Q8_0.gguf | Q8_0 | 705 MB |
From the source README
parakeet-tdt-0.6b-v3: transcribe.cpp GGUF
GGUF conversions of nvidia/parakeet-tdt-0.6b-v3 for use
with transcribe.cpp.
Ported from upstream commit
6d590f7,
pinned 2026-04-16.
Validated against the NeMo reference at transcribe.cpp commit
bf0d0b7
on 2026-04-18.
Offline multilingual speech-to-text covering 25 European languages. A
0.6B-parameter Conformer encoder with a TDT/RNNT transducer decoder. Takes
a 16 kHz mono WAV and produces a transcript with optional token-level
timestamps. Not a streaming model and does not translate.
Downloads
| Quantization | Download | Size | WER (LibriSpeech test-clean) |
| --- | --- | ---: | ---: |
| F32 | parakeet-tdt-0.6b-v3-F32.gguf | 2.51 GB | 1.95% |
| F16 | parakeet-tdt-0.6b-v3-F16.gguf | 1.26 GB | 1.95% |
| Q8_0 | parakeet-tdt-0.6b-v3-Q8_0.gguf | 740 MB | 1.94% |
| Q6_K | parakeet-tdt-0.6b-v3-Q6_K.gguf | 610 MB | 1.93% |
| Q5_K_M | parakeet-tdt-0.6b-v3-Q5_K_M.gguf | 549 MB | 1.92% |
| Q4_K_M | parakeet-tdt-0.6b-v3-Q4_K_M.gguf | 485 MB | 1.98% |
WER on the…
Source: https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v3-gguf
Card id model:hf:handy-computer/parakeet-tdt-0.6b-v3-gguf · collected 2026-10-02 20:59 UTC · JSON