moonshine tiny zh needs about 0.6 GB of memory at F16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.0 GB (Q8_0) to 0.1 GB (F32).
Moonshine tiny zh – 27M‑parameter Chinese speech recognizer
Moonshine tiny zh is a sequence‑to‑sequence ASR model trained for Mandarin. It transcribes 16 kHz raw PCM audio into Chinese text. The model is lightweight and designed for low‑resource deployments.
Good at
- Chinese speech transcription
- Low‑memory inference
- Fast decoding with transcribe.cpp
Limits
- No vision or translation support
- Limited to Mandarin only
- Requires 16 kHz mono WAV input
Best for
- Embedded speech‑to‑text devices
- Research prototypes needing small ASR
- Edge‑AI applications with 8 GB VRAM
Who it’s for. Developers building Chinese speech recognition systems on constrained hardware. The model is suitable for research and non‑commercial use; commercial use requires registration with Moonshine AI.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F32 | 0.1 GB | 0.6 GB | Fits | Get file → |
For 8 GB VRAM, Q8_0 (0.04 GB) is recommended, using about 0.5 GB memory at 8 k context. If more precision is needed, F16 (0.06 GB) uses roughly 0.6 GB. F32 (0.11 GB) is the largest and consumes about 0.6 GB. Estimates are approximate.
What GPU do you need for moonshine tiny zh?
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 (0.1 GB file, about 0.6 GB in use).
Which moonshine tiny zh quant should you choose?
F16 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about moonshine tiny zh
How much VRAM does moonshine tiny zh need?
About 0.6 GB at F16 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 moonshine tiny zh on an 8 GB GPU?
Yes, with F32: 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 zh GGUF?
It depends on the quant: Q8_0 is 0.0 GB, F16 is 0.1 GB, F32 is 0.1 GB.
Where can I download moonshine tiny zh GGUF?
The files are on Hugging Face in the handy-computer/moonshine-tiny-zh-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 zh use?
Hugging Face lists the license as other. 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 zh on 8 GB VRAM?
Yes. The Q8_0 quantization file is 0.04 GB and uses about 0.5 GB memory at 8 k context, fitting comfortably on 8 GB VRAM.
Does the model support timestamps?
No. The model outputs transcript‑only text without timestamps.
Is the model suitable for English speech?
No. It is trained exclusively for Mandarin Chinese and does not support other languages.