Moonshine Base (Japanese) 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 0.1 GB (Q8_0) to 0.2 GB (F32).
Moonshine Base (Japanese) – 62M parameter Japanese speech transcription model
Moonshine Base (Japanese) is a 62M parameter encoder‑decoder transformer fine‑tuned for Japanese speech transcription. It processes 16 kHz raw PCM audio and outputs transcript text only. The model is available in multiple GGUF quantizations.
Good at
- Japanese speech transcription
- Low‑parameter inference
- Fast generation
Limits
- No vision or translation support
- Single‑language only
- License requires registration for commercial use
Best for
- Research on Japanese ASR
- Embedded speech recognition
- Rapid prototyping of Japanese transcription tools
Who it’s for. Researchers and developers needing a lightweight Japanese speech-to-text model. The model is free for research and non‑commercial use; commercial deployment requires a license from Moonshine AI.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F32 | 0.2 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, the Q8_0 quant (0.08 GB file, 0.6 GB memory at 8 k context) is suitable. If more memory is available, F16 (0.13 GB, 0.6 GB) or F32 (0.25 GB, 0.8 GB) can be used for higher precision. Memory estimates are approximate.
What GPU do you need for Moonshine Base (Japanese)?
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 (0.2 GB file, about 0.8 GB in use).
Which Moonshine Base (Japanese) 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 0.1 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 Base (Japanese)
How much VRAM does Moonshine Base (Japanese) 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 Base (Japanese) on an 8 GB GPU?
Yes, with F32: the 0.2 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 Moonshine Base (Japanese) GGUF?
It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.1 GB, F32 is 0.2 GB.
Where can I download Moonshine Base (Japanese) GGUF?
The files are on Hugging Face in the handy-computer/moonshine-base-ja-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 Base (Japanese) 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 Q8_0 on 8 GB VRAM?
Yes. Q8_0 requires about 0.6 GB of VRAM at 8 k context, well within 8 GB.
Does the model support multiple languages?
No. It is trained only for Japanese and does not perform translation or language detection.
Is the model suitable for commercial use?
Commercial use requires a license from Moonshine AI; the model is free for research and non‑commercial use.