Parakeet TDT 0.6B v2 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 TDT 0.6B v2 – 600 M‑parameter English speech‑to‑text model
Parakeet TDT 0.6B v2 is a 600‑million‑parameter automatic speech recognition model. It delivers high‑quality English transcription with punctuation, capitalization, and accurate word‑level timestamps. The model is built on FastConformer‑TDT architecture and supports audio up to 24 minutes in a single pass.
Good at
- Accurate word‑level timestamps
- Automatic punctuation and capitalization
- Robust transcription of spoken numbers and song lyrics
Limits
- No multilingual support – English only
- Requires 16 kHz mono WAV input
- License CC‑BY‑4.0
Best for
- Transcribing podcasts and interviews
- Generating subtitles for videos
- Voice‑assistant backend
Who it’s for. Developers, researchers, and industry professionals building speech‑to‑text applications. The model is suitable for commercial and non‑commercial use under CC‑BY‑4.0.
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 | 2.5 GB | 3.3 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (0.48 GB) or Q5_K_M (0.54 GB) are suitable, using about 1–1.1 GB of VRAM at 8 k context. For 4 GB VRAM, Q4_K_M is recommended. Higher precision quants (Q6_K, Q8_0, F16, F32) require more memory and are not advised for low‑budget GPUs.
What GPU do you need for Parakeet TDT 0.6B v2?
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 TDT 0.6B v2 quant should you choose?
Q4_K_M is the usual starting point for Parakeet TDT 0.6B v2: 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 TDT 0.6B v2
How much VRAM does Parakeet TDT 0.6B v2 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 TDT 0.6B v2 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 TDT 0.6B v2 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 2.5 GB.
Where can I download Parakeet TDT 0.6B v2 GGUF?
The files are on Hugging Face in the handy-computer/parakeet-tdt-0.6b-v2-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 TDT 0.6B v2 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 TDT 0.6B v2 on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quantizations will fit within 8 GB VRAM, with approximate memory usage of 1–1.1 GB at 8 k context.
Does the model support multilingual transcription?
No, the v2 model is English only. Multilingual support is available in the v3 release.
What license applies to this model?
The model is released under the CC‑BY‑4.0 license, allowing commercial and non‑commercial use with attribution.