drama-3 needs about 34.0 GB of memory at Q6_K (a 29.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 20.8 GB (Q4_K) to 71.6 GB (F16).
35B‑parameter text‑to‑speech model for multi‑character scenes
Drama 3 is a 35 B parameter speech model that supports up to 16 simultaneous speakers and voice cloning. It uses a hybrid attention backbone and a codebook‑MTP audio decoder. The model is available in several GGUF quantizations for speech.cpp.
Good at
- Multi‑speaker generation
- Voice cloning
- Long‑form text streaming
Limits
- Requires speech.cpp 0.8.8+
- No vision support
- Large VRAM needed for higher quants
Best for
- Audio book narration
- Interactive dialogue systems
- Voice‑over production
Who it’s for. Developers building text‑to‑speech applications that need multiple characters or custom voice cloning. The model is suitable for production serving on GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 20.8 GB | 23.8 GB | Too big | Get file → | |
| Q5_K | 25.2 GB | 28.7 GB | Too big | Get file → | |
| Q6_K | 29.9 GB | 34.0 GB | Too big | Get file → | |
| Q8_0 | 38.5 GB | 43.6 GB | Too big | Get file → | |
| F16 | 71.6 GB | 80.7 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K (≈24 GB memory at 8 k context). With 16 GB VRAM Q5_K (≈29 GB) is feasible. For 32 GB VRAM Q6_K (≈34 GB) or Q8_0 (≈44 GB) can be used, but memory is approximate.
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K (20.8 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K (25.2 GB file, about 28.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (38.5 GB file, about 43.6 GB in use).
Which drama-3 quant should you choose?
Q6_K (29.9 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 20.8 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 drama-3
How much VRAM does drama-3 need?
About 34.0 GB at Q6_K with an 8K context window. That is the 29.9 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 23.8 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: Q4_K is 20.8 GB, Q5_K is 25.2 GB, Q6_K is 29.9 GB, Q8_0 is 38.5 GB, F16 is 71.6 GB.
Where can I download drama-3 GGUF?
The files are on Hugging Face in the sakasegawa/drama-3-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 on 8 GB VRAM?
Use the Q4_K quant; it requires about 24 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does Drama 3 support image inputs?
No, Drama 3 is a speech model and does not process vision data.
What languages can Drama 3 speak?
It can speak in any of 83 languages, as a single speaker or a scene of up to 16.