Pomni/distil-small.en-ggml-allquants

Distil-Small.en quants

This is a repository of GGML quants for distil-small.en (a Whisper-based transcription model), 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.

List of Quants

Clicking on a link will download the corresponding quant instantly.

Link	Quant	Size	Notes
GGML	F32	665 MB	Likely overkill.
GGML	F16	336 MB	Performs better than Q8_0 for noisy audio and music.
GGML	Q8_0	188 MB	Sweet spot; superficial quality loss at nearly double the speed.
GGML	Q6_K	148 MB
GGML	Q5_K	127 MB
GGML	Q5_1	137 MB
GGML	Q5_0	127 MB	Last "good" quant; anything below loses quality rapidly.
GGML	Q4_K	106 MB	Might not have lost too much quality, but I'm not sure.
GGML	Q4_1	117 MB
GGML	Q4_0	106 MB
GGML	Q3_K	84.9 MB
GGML	Q2_K	68.4 MB	Completely non-sensical outputs.

The F32 quant was taken from distil-whisper/distil-small.en/ggml-distil-small.en.fp32.bin, and the F16 quant was taken from distil-whisper/distil-small.en/ggml-distil-small.en.bin.

Questions you may have

Why do the "K-quants" not work for me?

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.

Are the K-quants "S", "M", or "L"?

The quantizer I was using was not specific about this, so I do not know about this either.

What program did you use to make these quants?

I used whisper.cpp v1.7.6 on Windows x64, leveraging CUDA 12.4.0.