WH

whisper large v3

WhisperGGUF by vonjackUpdated 2024-05-04
Download on Hugging Face
Parameters1.6B
Context—
Layers—
Architecture—
Smallest quant1.7 GB
Quick answer

whisper large v3 needs about 2.4 GB of memory at Q8_0 (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.7 GB (Q8_0) to 3.1 GB (F16).

Whisper large v3 GGUF model for speech recognition

Whisper large v3 is a 1.6 billion‑parameter model available in GGUF format. It is optimized for whisper.cpp and released under the Apache‑2.0 license.

Good at

  • Speech transcription
  • Audio transcription
  • Multilingual audio

Limits

  • No vision support
  • No context beyond 8 k tokens
  • No mixture of experts

Best for

  • Transcribing podcasts
  • Generating subtitles
  • Audio data labeling

Who it’s for. Developers building speech‑to‑text applications who need a lightweight, open‑source model. The model is suitable for local inference on machines with GPU or CPU support for whisper.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.7 GB 2.4 GB
Fits Get file →
F163.1 GB 4.0 GB
Fits Get file →

For 8 GB VRAM, use the Q8_0 quantization (file size 1.66 GB, estimated memory 2.4 GB at 8 k context). If more memory is available, the F16 quant (3.1 GB, 4 GB memory) provides higher precision.

What GPU do you need for 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 (3.1 GB file, about 4.0 GB in use).

Which whisper large v3 quant should you choose?

Q8_0 (1.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters1.6B

Source

Quantized byvonjack
FamilyWhisper
Licenseapache-2.0
Downloads (HF)1,093
Last updated2024-05-04

Frequently asked questions about whisper large v3

How much VRAM does whisper large v3 need?

About 2.4 GB at Q8_0 with an 8K context window. That is the 1.7 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 whisper large v3 on an 8 GB GPU?

Yes, with F16: the 3.1 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of whisper large v3 GGUF?

It depends on the quant: Q8_0 is 1.7 GB, F16 is 3.1 GB.

Where can I download whisper large v3 GGUF?

The files are on Hugging Face in the vonjack/whisper-large-v3-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 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 Whisper large v3 on 8 GB VRAM?

Yes, the Q8_0 quantization requires about 2.4 GB of VRAM at 8 k context, which fits within 8 GB.

Does this model support vision tasks?

No, Whisper large v3 is a speech‑to‑text model and does not support vision.

Similar models

Browse all →

More from vonjack

All by vonjack →

More Whisper models

All Whisper →

Other tiny models

All tiny models →