whisper small needs about 0.7 GB of memory at Q4_1 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.1 GB (Q2_K) to 0.3 GB (Q8_0).
Whisper Small quantized for efficient speech recognition
Whisper Small is a 0.242B parameter encoder‑decoder model for automatic speech recognition. It is available in multiple GGUF quantizations ranging from Q2_K to Q8_0. The model is licensed under MIT and supports English and multilingual speech tasks.
Good at
- Fast inference on low‑end GPUs
- Small file size
- Low memory footprint
Limits
- No vision support
- Limited to 8k context tokens
- Requires WhisperProcessor for audio preprocessing
Best for
- Transcribing short audio clips
- Real‑time voice assistants
- Batch processing of speech datasets
Who it’s for. Developers building lightweight speech recognition pipelines. Researchers needing a small, open‑source model for experimentation. Engineers deploying on edge devices with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_0 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_K | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_1 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K (0.15 GB) or Q5_0 (0.18 GB) are suitable, using about 0.7 GB RAM at 8k context. For 4 GB VRAM, Q2_K (0.09 GB) or Q3_K (0.11 GB) fit, with ~0.6 GB RAM. Higher quants like Q8_0 (0.26 GB) require more memory but offer better quality.
What GPU do you need for whisper small?
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 Q8_0 (0.3 GB file, about 0.8 GB in use).
Which whisper small quant should you choose?
Q4_1 (0.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about whisper small
How much VRAM does whisper small need?
About 0.7 GB at Q4_1 with an 8K context window. That is the 0.2 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 small on an 8 GB GPU?
Yes, with Q8_0: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of whisper small GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K is 0.1 GB, Q4_0 is 0.1 GB, Q4_0 is 0.1 GB, Q4_K is 0.1 GB, Q4_1 is 0.2 GB and 7 more.
Where can I download whisper small GGUF?
The files are on Hugging Face in the oxide-lab/whisper-small-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 small 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 Small on 8 GB VRAM?
Yes, Q4_K or Q5_0 quantizations fit within 8 GB VRAM, using roughly 0.7 GB RAM at 8k context.
Does this model support speech translation?
Yes, Whisper Small can perform translation when provided the appropriate context tokens.
What license applies to the quantized models?
The quantized models are released under the MIT license, same as the original Whisper.