whisper large v3 turbo needs about 1.0 GB of memory at Q4_K (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.5 GB (Q4_K) to 0.5 GB (Q4_1).
Whisper large‑v3‑turbo – fast, lightweight ASR model
Whisper large‑v3‑turbo is a pruned version of Whisper large‑v3 with only 4 decoding layers, providing faster inference. It retains the same architecture and training data as the parent model, offering robust speech recognition and translation.
Good at
- Fast inference with reduced decoding layers
- Zero‑shot speech recognition across many languages
- Automatic language detection
Limits
- No vision support
- Requires 8 k context for memory estimates
- MIT license only
Best for
- Transcribing short audio clips
- Real‑time speech transcription
- Batch processing of audio files
Who it’s for. Developers building lightweight ASR applications or services that need quick transcription without sacrificing too much accuracy. It is suitable for edge devices or environments with limited GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q4_1 | 0.5 GB | 1.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (0.48 GB file, ~1 GB memory at 8k context). If 8 GB is insufficient, Q4_1 (0.53 GB file, ~1.1 GB memory) is also viable. Both are approximate memory estimates.
What GPU do you need for whisper large v3 turbo?
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 Q4_1 (0.5 GB file, about 1.1 GB in use).
Which whisper large v3 turbo quant should you choose?
Q4_K (0.5 GB) is the middle option in this repository. 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
Source
Frequently asked questions about whisper large v3 turbo
How much VRAM does whisper large v3 turbo need?
About 1.0 GB at Q4_K 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 whisper large v3 turbo on an 8 GB GPU?
Yes, with Q4_1: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of whisper large v3 turbo GGUF?
It depends on the quant: Q4_K is 0.5 GB, Q4_1 is 0.5 GB.
Where can I download whisper large v3 turbo GGUF?
The files are on Hugging Face in the xkeyC/whisper-large-v3-turbo-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 turbo use?
Hugging Face lists the license as mit. 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‑turbo on 8 GB VRAM?
Yes, the Q4_K quantized model requires about 1 GB memory at 8k context, fitting comfortably on 8 GB VRAM.
Does this model support speech translation?
Yes, Whisper can perform translation to English when the task is set to "translate".
What license applies to this model?
The model is released under the MIT license.