parakeet rnnt 0.6b needs about 0.9 GB of memory at Q4_K (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q4_K) to 1.2 GB (F16).
Parakeet RNNT 0.6B – ASR model for lower‑case English transcription
Parakeet RNNT 0.6B is a 0.617 billion‑parameter ASR model that transcribes 16 kHz mono‑channel audio into lower‑case English text. It is an XL FastConformer Transducer model developed by NVIDIA NeMo and Suno.ai. The model is released under CC‑BY‑4.0.
Good at
- Transcribing 16 kHz mono audio
- Lower‑case English text output
- FastConformer architecture
Limits
- No vision support
- Requires 8 k context for memory estimates
- CC‑BY‑4.0 license requires attribution
Best for
- Speech-to-text pipelines
- Voice‑assistant transcription
- Audio data labeling
Who it’s for. Developers building speech recognition systems that need a lightweight, open‑source model. The model is suitable for integration with NeMo, Transformers, or CrispASR.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.4 GB | 0.9 GB | Fits | Get file → | |
| F16 | 1.2 GB | 1.9 GB | Fits | Get file → |
For 8 GB VRAM use the Q4_K quantization (file size 0.4 GB, estimated 0.9 GB memory at 8 k context). If more memory is available, the F16 quantization (1.24 GB, 1.9 GB memory) offers higher precision.
What GPU do you need for parakeet rnnt 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 F16 (1.2 GB file, about 1.9 GB in use).
Which parakeet rnnt 0.6b quant should you choose?
Q4_K (0.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about parakeet rnnt 0.6b
How much VRAM does parakeet rnnt 0.6b need?
About 0.9 GB at Q4_K with an 8K context window. That is the 0.4 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 rnnt 0.6b on an 8 GB GPU?
Yes, with F16: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of parakeet rnnt 0.6b GGUF?
It depends on the quant: Q4_K is 0.4 GB, F16 is 1.2 GB.
Where can I download parakeet rnnt 0.6b GGUF?
The files are on Hugging Face in the cstr/parakeet-rnnt-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 rnnt 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 RNNT on 8 GB VRAM?
Yes, the Q4_K quantization requires about 0.9 GB memory at 8 k context, well within 8 GB VRAM.
What license does this model use?
The model is released under the CC‑BY‑4.0 license, requiring attribution.
Does this model support other languages?
No, it only transcribes lower‑case English alphabet.