DI

distil whisper large v3

DistilGGUF by FL33TW00D-HFUpdated 2024-06-25
Download on Hugging Face
Parameters756M
Context—
Layers—
Architecture—
Smallest quant0.4 GB
Quick answer

distil whisper large v3 needs about 1.4 GB of memory at Q8_0 (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.4 GB to 1.5 GB (F16).

Distil Whisper Large V3 – lightweight speech‑to‑text model

Distil Whisper Large V3 is a distilled version of the Whisper large model. It contains 0.756 billion parameters and is released under the apache‑2.0 license. The model is available in several GGUF quantizations.

Good at

  • Fast inference on modest hardware
  • Efficient memory usage
  • Supports multiple languages

Limits

  • No vision support
  • Limited to 8 k context
  • Requires at least 1 GB VRAM for Q8_0

Best for

  • Transcribing short audio clips
  • Real‑time voice assistants
  • Batch processing of audio files

Who it’s for. Developers and researchers needing a lightweight speech‑to‑text model that balances speed and accuracy. The model is suitable for edge deployments and low‑resource environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.0 GB
Fits Get file →
Q8_00.8 GB 1.4 GB
Fits Get file →
F161.5 GB 2.2 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.83 GB file, ~1.4 GB memory). For 4 GB VRAM, use unknown quant (0.45 GB file, ~1 GB memory). For higher precision, F16 (1.52 GB file, ~2.2 GB memory) is available but needs more VRAM.

What GPU do you need for distil whisper large v3?

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 (1.5 GB file, about 2.2 GB in use).

Which distil whisper large v3 quant should you choose?

Q8_0 (0.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is the first one in the table at 0.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters756M

Source

Quantized byFL33TW00D-HF
FamilyDistil
Licenseapache-2.0
Downloads (HF)1,029
Last updated2024-06-25

Frequently asked questions about distil whisper large v3

How much VRAM does distil whisper large v3 need?

About 1.4 GB at Q8_0 with an 8K context window. That is the 0.8 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 distil whisper large v3 on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of distil whisper large v3 GGUF?

It depends on the quant: file is 0.4 GB, Q8_0 is 0.8 GB, F16 is 1.5 GB.

Where can I download distil whisper large v3 GGUF?

The files are on Hugging Face in the FL33TW00D-HF/distil-whisper-large-v3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does distil whisper large v3 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 this model on 8 GB VRAM?

Yes, the Q8_0 quantization requires about 1.4 GB VRAM at 8 k context, which fits within 8 GB.

Is the model licensed for commercial use?

It is released under the apache‑2.0 license, which allows commercial use.

Does the model support vision tasks?

No, this model does not support vision capabilities.

Similar models

Browse all →

More from FL33TW00D-HF

All by FL33TW00D-HF →

More Distil models

All Distil →

Other tiny models

All tiny models →