NVIDIA MagpieTTS multilingual 357M needs about 0.9 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.3 GB (Q8_0) to 0.6 GB (F16).
NVIDIA MagpieTTS multilingual 357M – 12‑language text‑to‑speech model
MagpieTTS is a 357M parameter encoder–decoder transformer that generates speech from text in 12 languages. It uses five English speaker voices and predicts discrete audio codec tokens for high‑fidelity synthesis. The model supports long‑form generation via a sliding‑window mechanism.
Good at
- Multilingual TTS in 12 languages
- High‑fidelity audio output
- Long‑form synthesis with sliding window
Limits
- No vision support
- Limited to 2048‑token context
- License is NVIDIA Open Model License
Best for
- Developers building multilingual TTS applications
- Researchers testing encoder–decoder TTS models
- Content creators needing high‑quality synthetic speech
Who it’s for. Engineers and researchers who need a lightweight multilingual TTS model for production or experimentation. The model is suitable for developers who can run it on GPUs with at least 8 GB VRAM and who require support for Arabic, Korean, and Portuguese in addition to the core languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F16 | 0.6 GB | 1.1 GB | Fits | Get file → |
For 8 GB VRAM, use the Q8_0 quantization (0.33 GB file, ~0.9 GB memory at 8k context). If more memory is available, the F16 quant (0.57 GB file, ~1.1 GB memory) offers higher precision. Both are approximate estimates.
What GPU do you need for NVIDIA MagpieTTS multilingual 357M?
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 (0.6 GB file, about 1.1 GB in use).
Which NVIDIA MagpieTTS multilingual 357M quant should you choose?
Q8_0 (0.3 GB) is the middle option in this repository. 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 NVIDIA MagpieTTS multilingual 357M
How much VRAM does NVIDIA MagpieTTS multilingual 357M need?
About 0.9 GB at Q8_0 with an 8K context window. That is the 0.3 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 NVIDIA MagpieTTS multilingual 357M on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NVIDIA MagpieTTS multilingual 357M GGUF?
It depends on the quant: Q8_0 is 0.3 GB, F16 is 0.6 GB.
What context length does NVIDIA MagpieTTS multilingual 357M support?
The GGUF header lists a trained context length of 2,048 tokens (2K).
Where can I download NVIDIA MagpieTTS multilingual 357M GGUF?
The files are on Hugging Face in the nvidia/magpie_tts_multilingual_357m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does NVIDIA MagpieTTS multilingual 357M 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 MagpieTTS on 8 GB VRAM?
Yes, the Q8_0 quantization requires about 0.9 GB of VRAM at 8k context, which fits within an 8 GB GPU. The F16 quant needs about 1.1 GB.
Does MagpieTTS support Korean?
Yes, the model includes Korean (ko) among its 12 supported languages.
What is the context length for inference?
The model was trained with a context of 2048 tokens and supports long‑form generation via a sliding‑window approach.