PA

ekko v1 tiny

ParakeetGGUF by RyeAIUpdated 2026-10-18
Download on Hugging Face
Parameters113M
Context—
Layers—
Architectureparakeet
Smallest quant0.1 GB
Quick answer

ekko v1 tiny needs about 0.7 GB of memory at Q5_K (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.1 GB (Q4_0) to 0.5 GB (F32).

Ekko v1 Tiny – compact Danish speech‑to‑text model

Ekko v1 Tiny is a 110‑million‑parameter Danish ASR model based on FastConformer RNN‑T. It outputs lowercase text with word timestamps. The model is optimized for local inference on NVIDIA GPUs.

Good at

  • Low‑latency Danish transcription
  • Word‑level timestamps
  • Compact size

Limits

  • No vision support
  • Requires NVIDIA GPU for best performance
  • License governed by NVIDIA Open Model License

Best for

  • Dictation of clear Danish speech
  • Reading aloud transcription
  • Offline speech‑to‑text on local devices

Who it’s for. Developers building Danish speech‑to‑text applications that need a lightweight model for local deployment. The model is suitable for Linux environments with NVIDIA Ampere, Blackwell or Hopper GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.1 GB 0.6 GB
Fits Get file →
Q4_K0.1 GB 0.6 GB
Fits Get file →
Q5_00.1 GB 0.7 GB
Fits Get file →
Q5_K0.1 GB 0.7 GB
Fits Get file →
Q6_K0.1 GB 0.7 GB
Fits Get file →
Q8_00.2 GB 0.7 GB
Fits Get file →
F160.3 GB 0.8 GB
Fits Get file →
F320.5 GB 1.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 or Q4_K (0.12 GB file, ~0.6 GB VRAM at 8 k context). For 12 GB VRAM, Q5_0 or Q5_K (0.13–0.14 GB file, ~0.7 GB VRAM). Higher precision F16 or F32 requires more memory and is not recommended for limited VRAM setups.

What GPU do you need for ekko v1 tiny?

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 ekko v1 tiny quant should you choose?

Q5_K (0.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. 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
Parameters113M

Source

Quantized byRyeAI
FamilyParakeet
Licenseother
Downloads (HF)735
Last updated2026-10-18

Frequently asked questions about ekko v1 tiny

How much VRAM does ekko v1 tiny need?

About 0.7 GB at Q5_K 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 ekko v1 tiny 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 ekko v1 tiny GGUF?

It depends on the quant: Q4_0 is 0.1 GB, Q4_K is 0.1 GB, Q5_0 is 0.1 GB, Q5_K is 0.1 GB, Q6_K is 0.1 GB, Q8_0 is 0.2 GB and 2 more.

Where can I download ekko v1 tiny GGUF?

The files are on Hugging Face in the RyeAI/ekko-v1-tiny repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ekko v1 tiny use?

Hugging Face lists the license as other. 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 Ekko v1 Tiny on 8 GB VRAM?

Yes, the Q4_0 and Q4_K quantizations are about 0.6 GB VRAM at 8 k context, fitting within 8 GB.

Does the model support multiple languages?

No, it is trained exclusively for Danish speech.

What is the context length supported?

The model was trained with an 8 k token context length.

Similar models

Browse all →

More Parakeet models

All Parakeet →

Other tiny models

All tiny models →