MA

Magenta RealTime 2

MagentaGGUF by audio-cppUpdated 2026-10-28
Download on Hugging Face
Parameters2.67B
Context—
Layers—
Architectureaudiocpp
Smallest quant1.3 GB
Quick answer

Magenta RealTime 2 needs about 2.2 GB of memory at F16 (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.3 GB (Q8_0) to 5.9 GB (F16).

Magenta RealTime 2 is a 2.67B-parameter Magenta model in GGUF format, quantized by audio-cpp. The repository has 4 quant files, from 1.3 GB (Q8_0) to 5.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.3 GB 2.0 GB
Fits Get file →
F161.5 GB 2.2 GB
Fits Get file →
Q8_03.7 GB 4.6 GB
Fits Get file →
F165.9 GB 7.1 GB
Fits Get file →

What GPU do you need for Magenta RealTime 2?

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 F16 (1.5 GB file, about 2.2 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.9 GB file, about 7.1 GB in use).

Which Magenta RealTime 2 quant should you choose?

F16 (1.5 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 1.3 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

Architectureaudiocpp
Parameters2.67B

Source

Quantized byaudio-cpp
FamilyMagenta
Licensecc-by-4.0
Downloads (HF)1,966
Last updated2026-10-28

Frequently asked questions about Magenta RealTime 2

How much VRAM does Magenta RealTime 2 need?

About 2.2 GB at F16 with an 8K context window. That is the 1.5 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 Magenta RealTime 2 on an 8 GB GPU?

Yes, with F16: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Magenta RealTime 2 GGUF?

It depends on the quant: Q8_0 is 1.3 GB, F16 is 1.5 GB, Q8_0 is 3.7 GB, F16 is 5.9 GB.

Where can I download Magenta RealTime 2 GGUF?

The files are on Hugging Face in the audio-cpp/Magenta-RealTime-2-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 Magenta RealTime 2 use?

Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from audio-cpp

All by audio-cpp →

Other tiny models

All tiny models →