MO

Moonshine Streaming Medium

MoonshineGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters266M
Context—
Layers—
Architecturemoonshine_streaming
Smallest quant0.3 GB
Quick answer

Moonshine Streaming Medium needs about 1.1 GB of memory at F16 (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.3 GB (Q8_0) to 1.1 GB (F32).

Moonshine Streaming Medium – lightweight 0.266B ASR model for low‑latency English transcription

Moonshine Streaming Medium is a sequence‑to‑sequence ASR model with a sliding‑window Transformer encoder and an autoregressive decoder. It is designed for on‑device, low‑latency English speech transcription on memory‑constrained hardware. The model uses a 50 Hz audio frontend and an ergodic encoder with no positional embeddings.

Good at

  • Low‑latency streaming ASR
  • On‑device inference
  • English speech transcription

Limits

  • No multilingual support
  • No vision or translation
  • Requires 16 kHz mono WAV

Best for

  • Live captioning on edge devices
  • Voice command systems
  • Real‑time transcription apps

Who it’s for. Developers building real‑time speech‑to‑text applications on edge hardware. The model is suitable for devices with sub‑1 GB memory budgets and modest compute (≈0.1–1 TOPS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.3 GB 0.8 GB
Fits Get file →
F160.5 GB 1.1 GB
Fits Get file →
F321.1 GB 1.7 GB
Fits Get file →

For 8 GB VRAM use the Q8_0 quant (0.3 GB file, ~0.8 GB memory at 8k context). With 4 GB VRAM the F16 quant (0.53 GB file, ~1.1 GB memory) is recommended. The F32 quant (1.07 GB file, ~1.7 GB memory) requires the largest memory budget.

What GPU do you need for Moonshine Streaming Medium?

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 (1.1 GB file, about 1.7 GB in use).

Which Moonshine Streaming Medium quant should you choose?

F16 (0.5 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 0.3 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_streaming
Parameters266M

Source

Quantized byhandy-computer
FamilyMoonshine
Licensemit
Downloads (HF)12,847
Last updated2026-10-16

Frequently asked questions about Moonshine Streaming Medium

How much VRAM does Moonshine Streaming Medium need?

About 1.1 GB at F16 with an 8K context window. That is the 0.5 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 Medium on an 8 GB GPU?

Yes, with F32: the 1.1 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Moonshine Streaming Medium GGUF?

It depends on the quant: Q8_0 is 0.3 GB, F16 is 0.5 GB, F32 is 1.1 GB.

Where can I download Moonshine Streaming Medium GGUF?

The files are on Hugging Face in the handy-computer/moonshine-streaming-medium-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 Medium 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 Medium on 8 GB VRAM?

Yes, the Q8_0 quant uses only about 0.8 GB of VRAM at 8k context, well within an 8 GB budget.

Does the model support multiple languages?

No, it is trained and evaluated only on English speech.

What audio format is required?

The model expects 16 kHz mono WAV files; other formats must be converted beforehand.

Other GGUFs of moonshine-streaming-medium

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Moonshine models

All Moonshine →

Other tiny models

All tiny models →