MO

Moonshine Base (Korean)

MoonshineGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters62M
Context—
Layers—
Architecturemoonshine
Smallest quant0.1 GB
Quick answer

Moonshine Base (Korean) 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 (Korean) – 62 M‑parameter ASR model

Moonshine Base (Korean) is a 62 M‑parameter sequence‑to‑sequence ASR model trained for Korean speech transcription. It uses a three‑layer Conv1d stem and outputs transcript‑only text. The model is available in several GGUF quantizations.

Good at

  • Korean speech transcription
  • Low‑resource deployment
  • Fast inference with small VRAM

Limits

  • No vision or translation support
  • No timestamps or language detection
  • Commercial use requires registration

Best for

  • Embedded speech‑to‑text devices
  • Real‑time transcription on low‑cost hardware
  • Research on Korean ASR

Who it’s for. AI developers building Korean speech recognition systems on constrained hardware. The model is suitable for research and non‑commercial use; commercial deployment requires registration with Moonshine AI.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.1 GB 0.6 GB
Fits Get file →
F320.2 GB 0.8 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.08 GB file, ~0.6 GB memory at 8k context). If 4 GB VRAM is available, F16 (0.13 GB file, ~0.6 GB memory) is a good choice. F32 (0.25 GB file, ~0.8 GB memory) is only recommended when ample VRAM is present.

What GPU do you need for Moonshine Base (Korean)?

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 (Korean) 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

Architecturemoonshine
Parameters62M

Source

Quantized byhandy-computer
FamilyMoonshine
Licenseother
Downloads (HF)901
Last updated2026-10-16

Frequently asked questions about Moonshine Base (Korean)

How much VRAM does Moonshine Base (Korean) 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 (Korean) 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 (Korean) 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 (Korean) GGUF?

The files are on Hugging Face in the handy-computer/moonshine-base-ko-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 (Korean) 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 Base (Korean) on 8 GB VRAM?

Yes. The Q8_0 quantization requires about 0.6 GB of VRAM at 8k context, well within an 8 GB budget.

Does the model support timestamps?

No. The Korean variant outputs transcript‑only text without timestamps.

Is commercial use allowed?

Commercial use requires registration with Moonshine AI and is limited to organizations under US$1M annual revenue.

Other GGUFs of moonshine-base-ko

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Moonshine models

All Moonshine →

Other tiny models

All tiny models →