Whisper Small needs about 0.7 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.2 GB (Q4_K_M) to 1.0 GB (F32).
Whisper Small – lightweight multilingual ASR and translation
Whisper Small is a 0.242 billion‑parameter encoder‑decoder model for automatic speech recognition and speech translation. It supports multilingual transcription and language detection, and can translate audio into English. The model is released under Apache‑2.0.
Good at
- Multilingual transcription
- Language detection
- Speech translation to English
Limits
- Requires 8 k context for inference
- No vision support
- Large memory for higher‑precision quants
Best for
- Transcribing short audio clips
- Translating spoken content to English
- Batch processing of multilingual recordings
Who it’s for. Developers building lightweight ASR or translation pipelines on limited GPU resources. Researchers needing a small, multilingual baseline model for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 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 → | |
| F16 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| F32 | 1.0 GB | 1.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.17 GB, ~0.7 GB RAM) or Q5_K_M (0.19 GB). If 16 GB VRAM is available, Q8_0 (0.27 GB) gives higher precision. F16 and F32 require more than 1 GB RAM and are not recommended for low‑budget setups.
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 F32 (1.0 GB file, about 1.6 GB in use).
Which Whisper Small quant should you choose?
Q4_K_M is the usual starting point for Whisper Small: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.3 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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_K_M 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 F32: the 1.0 GB file needs about 1.6 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: Q4_K_M is 0.2 GB, Q5_K_M is 0.2 GB, Q6_K is 0.2 GB, Q8_0 is 0.3 GB, F16 is 0.5 GB, F32 is 1.0 GB.
Where can I download Whisper Small GGUF?
The files are on Hugging Face in the handy-computer/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 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 Small on 8 GB VRAM?
Yes, the Q4_K_M or Q5_K_M quantizations fit within 8 GB VRAM and use about 0.7 GB of RAM at 8 k context.
Does Whisper Small support image inputs?
No, Whisper Small is an audio‑only model and does not process vision data.
What license applies to Whisper Small?
The model is released under the Apache‑2.0 license, inherited from the parent model.