Downloads · 30 days
0
Pomni/whisper-large-v3-turbo-ggml-allquants
whisper-large-v3-turbo-ggml-allquants is a automatic speech recognition model from Pomni. Use it when you need speech turned into text. The card lists the license as mit.
This is a repository of GGML quants for whisper-large-v3-turbo, for use with whisper.cpp.
Downloads · 30 days
0
Access
Public
Updated Aug 29, 2025
Repo size
7.1 GB
Likes
0
Public
Click a slice to open those files.
.bin7.1 GB · 100%
From the Hugging Face model README
This is a repository of GGML quants for whisper-large-v3-turbo, for use with whisper.cpp.
If you are looking for a program to run this model with, then I would recommend EasyWhisper UI, as it is user-friendly, has a GUI, and will automate a lot of the hard stuff for you.
Clicking on a link will download the corresponding quant instantly.
| Link | Quant | Size | Notes |
|---|---|---|---|
| GGML | F16 | 1.62 GB | Performs better than Q8_0 for noisy audio and music. |
| GGML | Q8_0 | 874 MB | Sweet spot; superficial quality loss at nearly double the speed. |
| GGML | Q6_K | 680 MB | |
| GGML | Q5_K | 574 MB | |
| GGML | Q5_1 | 624 MB | |
| GGML | Q5_0 | 574 MB | Last "good" quant; anything below loses quality rapidly. |
| GGML | Q4_K | 474 MB | Might not have lost too much quality, but I'm not sure. |
| GGML | Q4_1 | 524 MB | |
| GGML | Q4_0 | 474 MB | |
| GGML | Q3_K | 368 MB | |
| GGML | Q2_K | 286 MB | Completely non-sensical outputs. |
The F16 quant was taken from ggerganov/whisper.cpp/ggml-large-v3-turbo.bin.
My guess is that your GPU might be too old to recognize them, considering that I have gotten the same error on my GTX 1080. If you would like to run them regardless, you can try switching to CPU inference.
The quantizer I was using was not specific about this, so I do not know about this either.
I used whisper.cpp v1.7.6 on Windows x64, leveraging CUDA 12.4.0.
Open a new discussion in the community tab about this, and I will look into the issue.