Parakeet Ultra needs about 1.0 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.5 GB (Q4_K_M) to 2.5 GB (F32).
Parakeet Ultra – 0.6B multilingual speech‑to‑text model
Parakeet Ultra is a 0.6 billion parameter speech‑to‑text model based on the parakeet architecture. It supports 25 European languages and outputs punctuated, cased transcripts with optional timestamps. The model is licensed under CC‑BY‑4.0.
Good at
- Multilingual ASR on 25 European languages
- Low word error rates on LibriSpeech and FLEURS
- Long‑form audio segmentation up to 30 s per segment
Limits
- No vision or translation support
- Requires 8 k context for quantized inference
- Large memory for full‑precision variants
Best for
- Transcribing podcasts and meetings
- Generating subtitles for multilingual videos
- Batch processing of long audio files
Who it’s for. Developers building offline multilingual speech‑to‑text pipelines. Researchers needing a compact, open‑licensed model for evaluation or deployment on GPUs or CPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| F16 | 1.3 GB | 1.9 GB | Fits | Get file → | |
| F32 | 2.5 GB | 3.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.49 GB, ~1 GB RAM) or Q5_K_M (0.55 GB, ~1.1 GB RAM). If 16 GB VRAM is available, Q6_K (0.61 GB, ~1.2 GB RAM) or Q8_0 (0.74 GB, ~1.3 GB RAM) provide higher precision. Full‑precision F16 and F32 require 1.9 GB and 3.3 GB RAM respectively and are best for accuracy‑critical use.
What GPU do you need for Parakeet Ultra?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F32 (2.5 GB file, about 3.3 GB in use).
Which Parakeet Ultra quant should you choose?
Q4_K_M is the usual starting point for Parakeet Ultra: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.7 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Parakeet Ultra
How much VRAM does Parakeet Ultra need?
About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Parakeet Ultra on an 8 GB GPU?
Yes, with F32: the 2.5 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Parakeet Ultra GGUF?
It depends on the quant: Q4_K_M is 0.5 GB, Q5_K_M is 0.5 GB, Q6_K is 0.6 GB, Q8_0 is 0.7 GB, F16 is 1.3 GB, F32 is 2.5 GB.
Where can I download Parakeet Ultra GGUF?
The files are on Hugging Face in the handy-computer/parakeet-ultra-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Parakeet Ultra use?
Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Parakeet Ultra on 8 GB VRAM?
Yes, with Q4_K_M or Q5_K_M quantizations the model fits within 8 GB VRAM and uses about 1–1.1 GB of RAM.
Does Parakeet Ultra support translation?
No, it only performs speech‑to‑text transcription and does not translate.