moonshine-tiny needs about 0.5 GB of memory at Q8_0 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.0 GB (Q4_K) to 0.1 GB.
Moonshine Tiny – lightweight ASR model for English speech transcription
Moonshine Tiny is a 27M parameter sequence‑to‑sequence ASR model. It transcribes English speech into text and runs efficiently on low‑resource hardware. The model is released under the MIT license and supports only English.
Good at
- Fast inference on CPUs
- Low memory footprint
- Accurate English transcription
Limits
- No vision or non‑English language support
- Requires 8 k context for memory estimates
- No fine‑tuning provided
Best for
- Embedded speech‑to‑text devices
- Real‑time transcription on edge hardware
- Low‑cost voice assistants
Who it’s for. Developers building speech recognition systems on constrained devices. The model is suitable for applications that need quick, accurate English transcription without heavy computational resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K (0.02 GB) is ideal, using about 0.5 GB memory at 8 k context. Q8_0 (0.03 GB) offers higher precision with similar memory usage. The unknown quant (0.11 GB) uses about 0.6 GB memory and may be chosen if higher quality is needed.
What GPU do you need for moonshine-tiny?
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 the main file (0.1 GB file, about 0.6 GB in use).
Which moonshine-tiny quant should you choose?
Q8_0 (0.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q4_K at 0.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about moonshine-tiny
How much VRAM does moonshine-tiny need?
About 0.5 GB at Q8_0 with an 8K context window. That is the 0.0 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 moonshine-tiny on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of moonshine-tiny GGUF?
It depends on the quant: Q4_K is 0.0 GB, Q8_0 is 0.0 GB, file is 0.1 GB.
Where can I download moonshine-tiny GGUF?
The files are on Hugging Face in the cstr/moonshine-tiny-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 moonshine-tiny 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 Moonshine Tiny on 8 GB VRAM?
Yes. The Q4_K quant uses about 0.5 GB memory at 8 k context, well within an 8 GB VRAM budget.
Does Moonshine Tiny support languages other than English?
No. The model is trained and evaluated only for English speech recognition.
What license applies to Moonshine Tiny?
The model is released under the MIT license, allowing free use and modification.