WH

whisper tiny

WhisperGGUF by FL33TW00D-HFUpdated 2024-06-17
Download on Hugging Face
Parameters38M
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

whisper tiny needs about 0.6 GB of memory at F16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (Q8_0) to 0.2 GB (F32).

Whisper Tiny: lightweight speech recognition model

Whisper Tiny is a small, open‑source speech recognition model with 0.038 billion parameters. It is available in several GGUF quantizations and is licensed under apache‑2.0.

Good at

  • Fast inference on low‑memory devices
  • Small model size
  • Low latency speech transcription

Limits

  • No vision support
  • Limited to speech recognition
  • Requires 8 k context for memory estimates

Best for

  • Transcribing short audio clips
  • Edge devices with limited VRAM
  • Rapid prototyping of speech tools

Who it’s for. Developers needing a quick, low‑resource speech recognition solution. Suitable for mobile or embedded applications where model size and speed are critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.0 GB 0.5 GB
Fits Get file →
F160.1 GB 0.6 GB
Fits Get file →
—0.1 GB 0.7 GB
Fits Get file →
F320.2 GB 0.7 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.04 GB file, 0.5 GB memory). If 16 GB VRAM is available, F16 (0.08 GB file, 0.6 GB memory) offers a balance of speed and precision. Larger models like F32 (0.15 GB file, 0.7 GB memory) provide higher quality at the cost of more memory.

What GPU do you need for whisper 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 (0.2 GB file, about 0.7 GB in use).

Which whisper tiny quant should you choose?

F16 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters38M

Source

Quantized byFL33TW00D-HF
FamilyWhisper
Licenseapache-2.0
Downloads (HF)6,024
Last updated2024-06-17

Frequently asked questions about whisper tiny

How much VRAM does whisper tiny need?

About 0.6 GB at F16 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 whisper tiny on an 8 GB GPU?

Yes, with F32: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of whisper tiny GGUF?

It depends on the quant: Q8_0 is 0.0 GB, F16 is 0.1 GB, file is 0.1 GB, F32 is 0.2 GB.

Where can I download whisper tiny GGUF?

The files are on Hugging Face in the FL33TW00D-HF/whisper-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 whisper tiny use?

Hugging Face lists the license as apache-2.0. 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 Whisper Tiny on 8 GB VRAM?

Yes, the Q8_0 quantization uses 0.5 GB of VRAM at 8 k context, well within an 8 GB budget.

Does Whisper Tiny support multiple languages?

The model is designed for speech recognition; language support is not specified in the provided data.

Similar models

Browse all →

More from FL33TW00D-HF

All by FL33TW00D-HF →

More Whisper models

All Whisper →

Other tiny models

All tiny models →