Drama 3 ConfigI needs about 25.4 GB of memory at its main file (a 24.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 24.3 GB to 28.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Drama 3 ConfigI – a 34.7B parameter text‑to‑speech model
Drama 3 ConfigI is a 34.7B parameter mixture‑of‑experts model built on the qwen35moe architecture. It supports multi‑speaker generation, voice cloning, and natural‑language control. The model is optimized for long‑form content and streaming TTS.
Good at
- Multi‑speaker TTS
- Voice cloning
- Long‑form text streaming
Limits
- Requires GPU with at least 30.1 GB VRAM for 8 k context
- No vision support
- License is other, not standard
Best for
- Streaming TTS on high‑end GPUs
- Voice cloning for multi‑character scenes
- Long‑form audio generation
Who it’s for. Engineers and researchers needing high‑capacity TTS with multi‑speaker support. Suitable for developers with access to large‑VRAM GPUs and the TurboQuant llama.cpp fork.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 24.3 GB | 25.4 GB | Too big | Get file → | |
| — | 28.9 GB | 30.1 GB | Too big | Get file → |
The available GGUF files are unquantized. The 24.27 GB file needs about 25.4 GB VRAM at 8 k context, while the 28.94 GB file needs about 30.1 GB. For a 24 GB GPU use the 24.27 GB file with CPU offload; for 30 GB+ GPUs use the 28.94 GB file. Memory estimates are approximate.
What GPU do you need for Drama 3 ConfigI?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is the main file (28.9 GB file, about 30.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Drama 3 ConfigI
How much VRAM does Drama 3 ConfigI need?
About 25.4 GB at its main file with an 8K context window. That is the 24.3 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 Drama 3 ConfigI on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 25.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Drama 3 ConfigI GGUF?
It depends on the quant: file is 24.3 GB, file is 28.9 GB.
What context length does Drama 3 ConfigI support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Drama 3 ConfigI GGUF?
The files are on Hugging Face in the thetom-ai/Drama-3-ConfigI-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 ConfigI 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.
Does this model support vision tasks?
No, it only supports text and audio generation.
What quantization options are available?
Only the unquantized variants are provided; no other quantizations are listed.