Parakeet CTC 0.6B 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 2.4 GB (F32).
Parakeet CTC 0.6B – 600M parameter ASR model for English speech transcription
Parakeet CTC 0.6B is a 600‑million parameter FastConformer‑Large encoder model trained with CTC loss. It transcribes 16 kHz mono‑channel audio into lowercase English text without punctuation. The model is released under CC‑BY‑4.0 and is available in multiple GGUF quantizations.
Good at
- Low‑latency offline transcription
- Fast inference with transcribe.cpp
- Supports 16 kHz mono WAV inputs
Limits
- No vision or translation support
- Requires 8 kB context for best performance
- License is CC‑BY‑4.0
Best for
- Transcribing podcasts or interviews
- Batch processing of audio files
- Integrating into offline speech‑to‑text pipelines
Who it’s for. Engineers and researchers building offline speech‑to‑text solutions that need a lightweight, fast model. The model is suitable for deployment on edge devices or servers with limited GPU memory.
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 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| F32 | 2.4 GB | 3.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.47 GB) or Q5_K_M (0.53 GB). If 12 GB VRAM is available, Q6_K (0.59 GB) or Q8_0 (0.72 GB) provide higher precision. F16 and F32 quantizations require 1.9 GB and 3.2 GB of VRAM respectively and are recommended only for high‑accuracy use cases.
What GPU do you need for Parakeet CTC 0.6B?
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 (2.4 GB file, about 3.2 GB in use).
Which Parakeet CTC 0.6B quant should you choose?
Q4_K_M is the usual starting point for Parakeet CTC 0.6B: 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 CTC 0.6B
How much VRAM does Parakeet CTC 0.6B 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 CTC 0.6B on an 8 GB GPU?
Yes, with F32: the 2.4 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Parakeet CTC 0.6B 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 1.2 GB, F32 is 2.4 GB.
Where can I download Parakeet CTC 0.6B GGUF?
The files are on Hugging Face in the handy-computer/parakeet-ctc-0.6b-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 CTC 0.6B 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 CTC 0.6B on 8 GB VRAM?
Yes, the Q4_K_M and Q5_K_M quantizations fit within 8 GB VRAM and provide acceptable performance.
Does the model support punctuation or capitalization?
No, the output is lowercase text without punctuation, as it uses greedy CTC decoding.
What audio format does the model accept?
The model accepts 16 kHz mono‑channel WAV files; other formats must be converted beforehand.