PA

Parakeet RNN-T 0.6B

ParakeetGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters617M
Context—
Layers—
Architectureparakeet
Smallest quant0.5 GB
Quick answer

Parakeet RNN-T 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 2.5 GB (F32).

Parakeet RNN‑T 0.6B – 600M‑parameter offline English speech‑to‑text model

Parakeet RNN‑T 0.6B is an ASR model that transcribes 16 kHz mono audio into lowercase English text. It uses a FastConformer‑Large encoder with an RNN‑T transducer decoder. The model is released under CC‑BY‑4.0 and is available in GGUF format for transcribe.cpp.

Good at

  • Accurate offline transcription
  • Low‑latency greedy decoding
  • Compact GGUF files

Limits

  • No punctuation or streaming support
  • Requires 16 kHz mono WAV input
  • Large memory for higher context

Best for

  • Embedded speech‑to‑text on edge devices
  • Batch transcription pipelines
  • Low‑resource ASR research

Who it’s for. Developers building offline speech‑to‑text applications that need a small, efficient model. Researchers testing FastConformer‑RNN‑T architectures. Teams deploying ASR in constrained environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.0 GB
Fits Get file →
Q5_K_M0.5 GB 1.1 GB
Fits Get file →
Q6_K0.6 GB 1.2 GB
Fits Get file →
Q8_00.7 GB 1.3 GB
Fits Get file →
F161.2 GB 1.9 GB
Fits Get file →
F322.5 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 RAM at 8 k context. If more memory is available, Q6_K (0.60 GB) or Q8_0 (0.73 GB) give slightly better precision. Full‑precision F16 or F32 require 1.24 GB or 2.47 GB respectively.

What GPU do you need for Parakeet RNN-T 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 (2.5 GB file, about 3.3 GB in use).

Which Parakeet RNN-T 0.6B quant should you choose?

Q4_K_M is the usual starting point for Parakeet RNN-T 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

Architectureparakeet
Parameters617M

Source

Quantized byhandy-computer
FamilyParakeet
Licensecc-by-4.0
Downloads (HF)10,721
Last updated2026-10-16

Frequently asked questions about Parakeet RNN-T 0.6B

How much VRAM does Parakeet RNN-T 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 RNN-T 0.6B 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 RNN-T 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 2.5 GB.

Where can I download Parakeet RNN-T 0.6B GGUF?

The files are on Hugging Face in the handy-computer/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 RNN-T 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 RNN‑T 0.6B on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_M quantizations; they fit within 8 GB VRAM and use about 1–1.1 GB RAM at 8 k context.

Does this model support punctuation?

No, the output is lowercase text without punctuation.

Is the model streaming capable?

No, it is an offline model and does not support streaming inference.

Other GGUFs of parakeet-rnnt-0.6b

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Parakeet models

All Parakeet →

Other tiny models

All tiny models →