Irodori-TTS-v4-Large needs about 4.2 GB of memory at Q6_K (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.6 GB (Q4_K) to 7.0 GB (F16).
Japanese TTS model with multi‑modal voice design and emoji style control
Irodori‑TTS‑v4‑Large is a 3.38 billion‑parameter model for Japanese text‑to‑speech. It uses a Rectified Flow Diffusion Transformer and supports reference audio, caption text, and emoji‑based style control. The model is available in several GGUF quantizations for speech.cpp.
Good at
- Zero‑shot voice cloning
- Emoji‑based style control
- Long‑reference voice cloning up to 120 s
Limits
- Requires speech.cpp 0.8.7 or later
- No vision support
- License: gemma
- No support for non‑Japanese text
Best for
- Generating Japanese voice clips with custom style
- Creating voice‑design demos
- Producing audio with embedded sound effects
Who it’s for. Developers and researchers building Japanese TTS applications who need fine‑grained control over voice identity and style. The model is suitable for projects that can run speech.cpp and handle the required memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q5_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 3.9 GB | 4.8 GB | Fits | Get file → | |
| F16 | 7.0 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (file size 2.62 GB, estimated memory 3.4 GB). For 12 GB VRAM, Q5_K (2.93 GB, 3.8 GB) or Q6_K (3.27 GB, 4.2 GB) are suitable. For 16 GB VRAM, Q8_0 (3.88 GB, 4.8 GB) or F16 (6.96 GB, 8.3 GB) can be used.
What GPU do you need for Irodori-TTS-v4-Large?
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 Q5_K (2.9 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.0 GB file, about 8.3 GB in use).
Which Irodori-TTS-v4-Large quant should you choose?
Q6_K (3.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q4_K at 2.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Irodori-TTS-v4-Large
How much VRAM does Irodori-TTS-v4-Large need?
About 4.2 GB at Q6_K with an 8K context window. That is the 3.3 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 Irodori-TTS-v4-Large on an 8 GB GPU?
Yes, with Q8_0: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Irodori-TTS-v4-Large GGUF?
It depends on the quant: Q4_K is 2.6 GB, Q5_K is 2.9 GB, Q6_K is 3.3 GB, Q8_0 is 3.9 GB, F16 is 7.0 GB.
Where can I download Irodori-TTS-v4-Large GGUF?
The files are on Hugging Face in the sakasegawa/Irodori-TTS-v4-Large-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 Irodori-TTS-v4-Large use?
Hugging Face lists the license as gemma. 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 Irodori‑TTS‑v4‑Large on 8 GB VRAM?
Yes, the Q4_K quantization requires about 3.4 GB of VRAM at 8k context, which fits in 8 GB.
Does the model support English text?
No, the model is trained for Japanese only and does not support other languages.
What software is needed to run the GGUF files?
The GGUF files run only in speech.cpp 0.8.7 or later; other GGUF readers cannot load them.