Parakeet TDT-CTC 110M needs about 0.6 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.1 GB (Q4_K_M) to 0.5 GB (F32).
Parakeet TDT-CTC 110M – 110 M‑parameter English speech‑to‑text model
Parakeet TDT-CTC 110M is an ASR model that transcribes English speech with punctuation and capitalization. It uses a Hybrid FastConformer encoder with a TDT/RNNT transducer decoder and can process up to 20 minutes of audio in a single pass.
Good at
- Fast, accurate transcription of English speech
- Handles long audio segments in one pass
- Provides punctuation and capitalization
Limits
- No vision support
- Requires 16 kHz mono‑WAV input
- CC‑BY‑4.0 license
Best for
- Transcribing podcasts or interviews
- Generating subtitles for videos
- Batch processing of long audio files
Who it’s for. Developers and content creators who need reliable offline English speech‑to‑text. The model is suitable for batch transcription workflows and can be integrated into existing pipelines via NeMo or transcribe.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| F32 | 0.5 GB | 1.0 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M or Q5_K_M (0.09–0.10 GB) are suitable, using ~0.6 GB memory at 8 k context. If 16 GB VRAM is available, Q6_K or Q8_0 (0.11–0.14 GB) provide higher precision with ~0.6–0.7 GB memory. F16 and F32 require 0.8–1 GB memory and are recommended only for systems with ample VRAM.
What GPU do you need for Parakeet TDT-CTC 110M?
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 (0.5 GB file, about 1.0 GB in use).
Which Parakeet TDT-CTC 110M quant should you choose?
Q4_K_M is the usual starting point for Parakeet TDT-CTC 110M: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 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-CTC 110M
How much VRAM does Parakeet TDT-CTC 110M need?
About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.1 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-CTC 110M on an 8 GB GPU?
Yes, with F32: the 0.5 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Parakeet TDT-CTC 110M GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q6_K is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB, F32 is 0.5 GB.
Where can I download Parakeet TDT-CTC 110M GGUF?
The files are on Hugging Face in the handy-computer/parakeet-tdt_ctc-110m-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-CTC 110M 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-CTC 110M on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quantizations, which use about 0.6 GB memory at 8 k context.
What audio format does the model accept?
16 kHz mono‑WAV files are required; other formats must be converted before inference.
Does the model support streaming inference?
No, it is a non‑streaming model and processes entire audio files at once.