moonshine-streaming-tiny needs about 0.5 GB of memory at Q4_K (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.0 GB (Q4_K) to 0.2 GB.
Moonshine Streaming Tiny – lightweight 34M ASR model for low‑latency edge devices
Moonshine Streaming Tiny is a 34M parameter sequence‑to‑sequence ASR model. It uses a 50 Hz raw‑waveform frontend, sliding‑window Transformer encoder, and autoregressive decoder. Designed for low‑latency, on‑device English speech transcription.
Good at
- Low‑latency streaming ASR
- Edge‑device deployment
- English voice commands
Limits
- No vision support
- English only
- Small context size
Best for
- Live captioning
- Voice‑command interfaces
- Real‑time transcription
Who it’s for. Developers building on‑device speech recognition solutions that require minimal memory and compute. Suitable for mobile, embedded, and IoT platforms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K variant (0.03 GB) uses about 0.5 GB at 8 k context and is ideal. If more memory is available, the unknown quant (0.18 GB) uses about 0.7 GB and may offer higher precision. Estimates are approximate.
What GPU do you need for moonshine-streaming-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 (0.2 GB file, about 0.7 GB in use).
Which moonshine-streaming-tiny quant should you choose?
Q4_K (0.0 GB) is the middle option in this repository. 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-streaming-tiny
How much VRAM does moonshine-streaming-tiny need?
About 0.5 GB at Q4_K 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-streaming-tiny on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of moonshine-streaming-tiny GGUF?
It depends on the quant: Q4_K is 0.0 GB, file is 0.2 GB.
Where can I download moonshine-streaming-tiny GGUF?
The files are on Hugging Face in the cstr/moonshine-streaming-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-streaming-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 Streaming Tiny on 8 GB VRAM?
Yes. The Q4_K variant requires only about 0.5 GB of VRAM at 8 k context, well within an 8 GB budget.
What languages does this model support?
English only. The model was trained and evaluated on English datasets.
Which quantization should I choose for best performance?
Use Q4_K for the lowest memory footprint. If you need higher precision and have extra memory, try the unknown quant variant.