Parakeet Redux
Parakeet Redux is a speech-to-text model (1.58-bit Parakeet 0.6B (178 MB)) from Moondream, released under the CC BY 4.0 license. The reviewed source lists 25 European languages (25 explicitly enumerated in our record), and the model is designed for batch-first transcription. Among the common setups we test, it ranks highest for CPU-only machines (#2 of 26 in the matcher).
A 1.58-bit (ternary) version of Parakeet TDT 0.6B v3 that fits in 178 MB and keeps its 25 languages and CC BY 4.0 license. Moondream reports 113× real time on eight x86 CPU cores with its Photon runtime; streaming and timestamps are not stated on the card. Ratings are provisional until independent benchmarks are available.
Key facts
| Provider | Moondream |
|---|---|
| Model family | Parakeet |
| Parameters | 1.58-bit Parakeet 0.6B (178 MB) |
| License | CC BY 4.0 · Attribution required — license text ↗ |
| Language coverage | 25 European languages · 25 enumerated in our record |
| Streaming | Batch-first (no streaming path in the reviewed source) |
| Timestamps | Not documented |
| Speaker diarization | No — needs a separate component |
| Speech translation | No |
| Documented runtimes | Photon (moondream package) — how to run it |
| Primary source | huggingface.co/moondream/parakeet-redux ↗ |
| Rating status | Provisional (added November 3, 2026) |
| Last reviewed |
Hardware and workload fit
These are Speech Model Match's conservative 1–5 editorial ratings, relative to the other 19 reviewed models. They come from model size, official memory guidance and documented runtimes — not from a universal benchmark. How the ratings work.
| Dimension | Rating | Scale |
|---|---|---|
| CPU-only fit | 5/5 | |
| Apple Silicon fit | 4/5 | |
| NVIDIA GPU fit | 3/5 | |
| Speed | 5/5 | |
| Accuracy (relative) | 3/5 | |
| Low memory use | 5/5 | |
| Long recordings | 4/5 | |
| Live / low latency | 2/5 | |
| Subtitle work | 2/5 | |
| Edge / low-power devices | 4/5 |
Where it is strong
- CPU-only fit: rated 5/5
- Apple Silicon fit: rated 4/5
- Speed: rated 5/5
- Low memory use: rated 5/5
- Long recordings: rated 4/5
- Edge / low-power devices: rated 4/5
What to check first
- No streaming path in the reviewed source — plan for file/batch transcription
- Live / low latency: rated 2/5
- Subtitle work: rated 2/5
- No native speaker diarization — pair it with a separate diarization pipeline if you need speaker labels
- Timestamp support is limited or runtime-dependent — test it if you need subtitles
- Commercial use is possible, but the license requires attribution.
How it ranks in common setups
Ranks come from the same deterministic matcher that runs on the homepage, applied to all 26 reviewed models. They are decision guidance, not accuracy claims.
| Setup | Rank | Fit score | Top match |
|---|---|---|---|
| Long recordings on an 8–12 GB NVIDIA GPU, balanced | #23 of 26 | 66/100 · Possible fit | Whisper turbo |
| Live captions or voice input (native streaming + timestamps, speed first) | #23 of 26 | 51/100 · Weak fit | Nemotron 3.5 ASR Streaming 0.6B |
| Subtitles with timing, accuracy first | #26 of 26 | 56/100 · Weak fit | Whisper medium |
| Meetings with speaker labels (diarization + timestamps) | #25 of 26 | 60/100 · Possible fit | VibeVoice-ASR 7B |
| CPU-only machine, low memory use | #2 of 26 | 78/100 · Strong fit | VibeVoice-ASR-BitNet |
| Apple Silicon with 8–16 GB unified memory, long recordings | #7 of 26 | 70/100 · Possible fit | Whisper small |
| Japanese live transcription (native streaming, speed first) | Not ranked (language not listed) | — | Nemotron 3.5 ASR Streaming 0.6B |
Supported languages
- Bulgarian
bg - Croatian
hr - Czech
cs - Danish
da - Dutch
nl - English
en - Estonian
et - Finnish
fi - French
fr - German
de - Greek
el - Hungarian
hu - Italian
it - Latvian
lv - Lithuanian
lt - Maltese
mt - Polish
pl - Portuguese
pt - Romanian
ro - Russian
ru - Slovak
sk - Slovenian
sl - Spanish
es - Swedish
sv - Ukrainian
uk
Compare coverage across every reviewed model in the language support matrix.
Community activity on Hugging Face
- Downloads, last 30 days
- 9,581
- Likes
- 317
- Repository last updated
- 23 Sept 2026
- Published on the Hub
- 18 Sept 2026
Figures from the Hugging Face Hub API, 11 Nov 2026. Source: huggingface.co/moondream/parakeet-redux ↗. Downloads count file downloads, not active users, and do not affect the matcher's scores. Compare all models.
How to run Parakeet Redux locally
Moondream runs its 1.58-bit Parakeet through the Photon runtime in the moondream Python package. Runtimes below are the ones the official model card or repository documents for this model (checked November 2, 2026).
- Photon (moondream package) ↗Official package · CPU (AVX-512 VNNI, NEON), Apple GPU (MPS) or CUDA
Install command shown in the official huggingface.co page ↗:
pip install moondream
Official hardware guidance: The model fits in 178 MB. Moondream reports 113× real time on eight x86 CPU cores (AMD EPYC 9575F) and about 38× on the CPU of an M2 MacBook Air. Source ↗
Whatever runtime you choose, measure speed and accuracy on your own audio with the benchmark tool; results differ a lot between runtimes, precision and hardware.
Before you deploy Parakeet Redux
A printable checklist built from the facts on this page. Tick it off before putting the model into production.
- Language. Confirm your language is in the 25-language list on this page, and test any accents or code-switching you expect.
- License. CC BY 4.0: Give appropriate credit, provide a link to the license and indicate if changes were made. Do not add terms or technical measures that restrict others from doing what the license permits. License guide.
- Install. Start from the official command:
pip install moondream(full run notes). - Audio input. Convert a sample of your real recordings to the format the runtime expects before benchmarking.
- Hardware. The model fits in 178 MB. Moondream reports 113× real time on eight x86 CPU cores (AMD EPYC 9575F) and about 38× on the CPU of an M2 MacBook Air.
- Features you rely on. For Parakeet Redux, no streaming path is documented; timestamps are not documented; speaker labels need a separate diarization component. Test each one you need with real audio.
- Measure. Run 10–20 representative clips, score them with the WER calculator and record speed in the benchmark workspace before you commit.
- Provisional ratings. This model was added on November 3, 2026; treat its hardware and workload ratings as estimates and weight your own measurements higher.
Alternatives and related models
Same family: Parakeet TDT 0.6B v3.
Similar fit profile: Granite Speech 5.0 470M TurboCTC (IBM, 470M), VibeVoice-ASR-BitNet (Microsoft, 0.3B quantized), Whisper base (OpenAI, 74M). Similarity is computed from the ten fit ratings plus streaming and diarization support.
| Fact | Parakeet Redux | Parakeet TDT 0.6B v3 |
|---|---|---|
| Provider · size | Moondream · 1.58-bit Parakeet 0.6B (178 MB) | NVIDIA · 600M |
| License | CC BY 4.0 Attribution required | CC BY 4.0 Attribution required |
| Languages | 25 European languages | 25 European languages |
| Streaming | Batch-first | Via runtime |
| Timestamps | Not documented | Yes |
| Speaker diarization | Separate pipeline | Separate pipeline |
| CPU · Apple · NVIDIA fit | 5/5 · 4/5 · 3/5 | 2/5 · 3/5 · 5/5 |
| Live · long recordings | 2/5 · 4/5 | 2/5 · 5/5 |
| Main runtime | Photon (moondream package) | NVIDIA NeMo |
Head-to-head pages: Parakeet TDT 0.6B v3 vs Parakeet Redux
Compare Parakeet Redux side by side
Guides that cover Parakeet Redux
- Parakeet v3 vs Nemotron 3.5 ASR Streaming
- Whisper vs Parakeet: which local ASR should you test first?
Check Parakeet Redux for your setup
Pick your language, hardware and workload to see this model's fit score, the reasons behind it and where it ranks against all reviewed models. Everything runs in your browser.
Common questions
Can I use Parakeet Redux commercially?
Commercial use is possible, but the license requires attribution. The listed license is CC BY 4.0; read the current license text ↗ before shipping a product, because terms can change. The license guide compares the obligations of all 26 reviewed models.
Does Parakeet Redux support real-time streaming?
No streaming path is documented in the reviewed source. Treat it as a file/batch transcription model.
Which languages does Parakeet Redux transcribe?
25 European languages. The full list of 25 explicitly enumerated languages is shown above.
Can Parakeet Redux tell speakers apart?
Not natively. Combine it with a dedicated diarization component and evaluate that component separately; the meetings guide covers this workflow.
Primary sources
Reviewed against primary sources on November 3, 2026. Model behavior, runtime support, language coverage and licenses can change; re-check the linked primary source before production use. See the full source directory.