Whisper Base (English) needs about 0.6 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.1 GB (Q4_K_M) to 0.3 GB (F32).
Whisper Base (English) – 0.0726 B parameters for English speech recognition
Whisper Base (English) is a 0.0726 B parameter encoder‑decoder transformer trained on 680k hours of labelled speech. It is an English‑only model for automatic speech recognition. The GGUF conversion supports transcribe.cpp usage.
Good at
- English speech recognition
- Short‑form transcription
- Low‑latency decoding
Limits
- No vision support
- Requires 16 kHz mono WAV
- License: Apache‑2.0
Best for
- Transcribing podcasts
- Generating subtitles
- Voice‑to‑text for apps
Who it’s for. Developers building lightweight ASR solutions on edge devices. Researchers needing a small, open‑source Whisper variant. Content creators seeking quick transcription of English audio.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F32 | 0.3 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q5_K_M (0.06 GB file, ~0.6 GB VRAM). For 4 GB VRAM, Q4_K_M is suitable. If more VRAM is available, Q8_0 or F16 offer higher precision.
What GPU do you need for Whisper Base (English)?
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 (0.3 GB file, about 0.8 GB in use).
Which Whisper Base (English) quant should you choose?
Q4_K_M is the usual starting point for Whisper Base (English): it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.4 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 Base (English)
How much VRAM does Whisper Base (English) need?
About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.1 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 Base (English) on an 8 GB GPU?
Yes, with F32: 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 Base (English) GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q6_K is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB, F32 is 0.3 GB.
Where can I download Whisper Base (English) GGUF?
The files are on Hugging Face in the handy-computer/whisper-base.en-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 Base (English) 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 Base on 4 GB VRAM?
Yes, the Q4_K_M quantized file is 0.06 GB and requires about 0.6 GB VRAM at 8k context, well within 4 GB.
Does this model support multilingual transcription?
No, Whisper Base is English‑only; multilingual transcription requires a multilingual checkpoint.
What license applies to this model?
The model is licensed under Apache‑2.0, inherited from the original OpenAI Whisper.