drama-3 needs about 12.2 GB of memory at IQ3_XXS (a 10.5 GB file) with an 8K context window, so it fits on a 16 GB GPU.
Compressed Fish Audio Drama 3 for Japanese and English voice cloning
drama-3-small is a compressed version of Fish Audio Drama 3. It supports multi‑speaker generation, voice cloning, and natural‑language control in Japanese and English. The model is pruned to 45% of expert slots and quantized to about 3 bits.
Good at
- Multi‑speaker TTS
- Voice cloning
- Inline tags and director notes
Limits
- No vision support
- Requires 12 GB VRAM or more
- License is other
Best for
- Short dialogue scripts
- Voice‑over production
- Character‑driven narration
Who it’s for. Developers and content creators needing realistic Japanese or English TTS with multi‑speaker capability. The model is suitable for production pipelines that can accommodate its VRAM requirement.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 10.5 GB | 12.2 GB | Too big | Get file → |
The only available quant is IQ3_XXS, 10.46 GB file size. It requires approximately 12.2 GB of VRAM at 8 k context. For systems with 8 GB VRAM, the model cannot be loaded. If you have 12 GB or more, IQ3_XXS is the recommended quant.
What GPU do you need for drama-3?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ3_XXS (10.5 GB file, about 12.2 GB in use).
Which drama-3 quant should you choose?
IQ3_XXS (10.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about drama-3
How much VRAM does drama-3 need?
About 12.2 GB at IQ3_XXS with an 8K context window. That is the 10.5 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 drama-3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of drama-3 GGUF?
It depends on the quant: IQ3_XXS is 10.5 GB.
Where can I download drama-3 GGUF?
The files are on Hugging Face in the pentacoxian-dev/drama3-small-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 drama-3 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 drama-3-small on 8 GB VRAM?
No. The IQ3_XXS quant requires about 12.2 GB of VRAM at 8 k context.
What languages does drama-3-small support?
Japanese and English voice cloning and generation.
Does drama-3-small support vision or image input?
No, the model only handles audio and text.