parakeet primeline 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).
600‑million‑parameter German ASR model optimized for speed and accuracy
parakeet primeline is a 0.6B‑parameter Automatic Speech Recognition model based on the FastConformer‑TDT architecture. It is fine‑tuned for German transcription and produces punctuated, cased text with optional token‑level timestamps. The model supports 25 languages and is available in multiple GGUF quantizations.
Good at
- High‑accuracy German transcription
- Fast inference with low‑precision quantizations
- Rich output with punctuation and timestamps
Limits
- Not a streaming model
- No translation capability
- Requires 16 kHz mono WAV input
Best for
- Subtitle generation for German media
- Real‑time captioning in enterprise settings
- Large‑scale German linguistic research
Who it’s for. Developers and researchers needing efficient German speech‑to‑text. The model is suitable for applications that require fast, accurate transcription without the need for streaming or translation.
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, Q4_K_M (0.49 GB) or Q5_K_M (0.55 GB) provide the best balance of speed and memory. If more VRAM is available, Q6_K (0.61 GB) or Q8_0 (0.74 GB) offer slightly higher precision. The F16 and F32 variants require 1.26 GB and 2.51 GB respectively and are recommended only when maximum precision is needed.
What GPU do you need for parakeet primeline?
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 primeline quant should you choose?
Q4_K_M is the usual starting point for parakeet primeline: 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 primeline
How much VRAM does parakeet primeline 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 primeline 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 primeline 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 primeline GGUF?
The files are on Hugging Face in the handy-computer/parakeet-primeline-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 primeline 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 primeline on 8 GB VRAM?
Yes, the Q4_K_M and Q5_K_M quantizations fit comfortably within 8 GB VRAM and use about 1–1.1 GB of memory at 8 k context.
Does this model support streaming inference?
No, parakeet primeline is not a streaming model and requires full audio input.
Can it transcribe languages other than German?
Yes, it retains multilingual support for 24 additional languages with correct casing and punctuation.