PA

parakeet rnnt 1.1b

ParakeetGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters1.07B
Context—
Layers—
Architectureparakeet
Smallest quant0.7 GB
Quick answer

parakeet rnnt 1.1b needs about 1.3 GB of memory at Q4_K (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.7 GB (Q4_K) to 2.1 GB (F16).

Parakeet RNNT 1.1B – ASR model for lower‑case English transcription

Parakeet RNNT 1.1B is a 1.07‑billion parameter speech‑to‑text model. It transcribes 16 kHz mono audio into lowercase English text. The model is released under CC‑BY‑4.0 and is available in GGUF format.

Good at

  • Transcribing 16 kHz mono audio
  • Lowercase English text output
  • FastConformer encoder

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • CC‑BY‑4.0 license

Best for

  • Real‑time speech transcription
  • Batch audio transcription
  • Integration with NeMo or Transformers

Who it’s for. Developers building speech‑to‑text pipelines who need a lightweight, open‑source ASR model. It is suitable for applications that require lower‑case English output and can run on consumer GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.7 GB 1.3 GB
Fits Get file →
F162.1 GB 2.9 GB
Fits Get file →

For 8 GB VRAM use the Q4_K quantization (0.68 GB file, ~1.3 GB memory). For higher precision or larger memory budgets use F16 (2.14 GB file, ~2.9 GB memory).

What GPU do you need for parakeet rnnt 1.1b?

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 (2.1 GB file, about 2.9 GB in use).

Which parakeet rnnt 1.1b quant should you choose?

Q4_K (0.7 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

Architectureparakeet
Parameters1.07B

Source

Quantized bycstr
FamilyParakeet
Licensecc-by-4.0
Downloads (HF)1,635
Last updated2026-08-02

Frequently asked questions about parakeet rnnt 1.1b

How much VRAM does parakeet rnnt 1.1b need?

About 1.3 GB at Q4_K with an 8K context window. That is the 0.7 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 1.1b on an 8 GB GPU?

Yes, with F16: the 2.1 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of parakeet rnnt 1.1b GGUF?

It depends on the quant: Q4_K is 0.7 GB, F16 is 2.1 GB.

Where can I download parakeet rnnt 1.1b GGUF?

The files are on Hugging Face in the cstr/parakeet-rnnt-1.1b-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 1.1b 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 quantized model requires about 1.3 GB of VRAM at 8 k context.

Does this model support vision tasks?

No, it is an audio‑only ASR model.

What license applies to this model?

The model is released under the CC‑BY‑4.0 license.

Other GGUFs of parakeet-rnnt-1.1b

Similar models

Browse all →

More from cstr

All by cstr →

More Parakeet models

All Parakeet →

Other tiny models

All tiny models →