DR

Drama 3 Windows

DramaGGUF by Eng-AhmdUpdated 2026-10-15
Download on Hugging Face
Parameters35.9B
Context—
Layers—
Architecturefish-speech-codec
Smallest quant1.6 GB
Quick answer

Drama 3 Windows needs about 26.6 GB of memory at Q4_K (a 23.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 1.6 GB to 23.3 GB.

35.9B MoE text-to-speech model for voice cloning and contextual editing on Windows

Drama 3 Windows is a 35.9B MoE text-to-speech model built on fish-speech-codec. It supports multi-speaker generation, voice cloning, and contextual editing. The model runs locally on Windows with CPU or CUDA execution.

Good at

  • Voice cloning with emotion and event tags
  • Contextual edits and continuity across long text
  • Multi-speaker scenes up to 16 characters

Limits

  • Requires large VRAM (≈26.6 GB for Q4_K)
  • 8 k token context length
  • No vision support

Best for

  • Local TTS with voice cloning
  • Editing spoken content with acoustic history
  • Multi-character dialogue generation

Who it’s for. Engineers and developers who need expressive, editable speech synthesis on Windows hardware. It is suitable for local deployment where GPU memory is available and custom voice conditioning is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.6 GB 2.3 GB
Fits Get file →
Q4_K23.3 GB 26.6 GB
Too big Get file →
—23.3 GB 26.6 GB
Too big Get file →

The Q4_K quantized file is 23.27 GB and needs about 26.6 GB VRAM at 8 k context. The unknown quant file is 1.57 GB and needs about 2.3 GB VRAM. For 8 GB VRAM use the unknown quant; for 16 GB VRAM use Q4_K; for >26 GB VRAM use Q4_K for full performance. Memory estimates are approximate.

What GPU do you need for Drama 3 Windows?

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 the main file (1.6 GB file, about 2.3 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.6 GB file, about 2.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.6 GB file, about 2.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (1.6 GB file, about 2.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (1.6 GB file, about 2.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (1.6 GB file, about 2.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K (23.3 GB file, about 26.6 GB in use).

Which Drama 3 Windows quant should you choose?

Q4_K (23.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is the first one in the table at 1.6 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturefish-speech-codec
Parameters35.9B

Source

Quantized byEng-Ahmd
FamilyDrama
Licenseother
Downloads (HF)16,629
Last updated2026-10-15

Frequently asked questions about Drama 3 Windows

How much VRAM does Drama 3 Windows need?

About 26.6 GB at Q4_K with an 8K context window. That is the 23.3 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 Windows on an 8 GB GPU?

Yes, with the smaller files: the 1.6 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Drama 3 Windows GGUF?

It depends on the quant: file is 1.6 GB, Q4_K is 23.3 GB, file is 23.3 GB.

Where can I download Drama 3 Windows GGUF?

The files are on Hugging Face in the Eng-Ahmd/Drama-3-Windows-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 Windows 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?

Yes, use the 1.57 GB unknown quant file which requires about 2.3 GB VRAM at 8 k context.

Does Drama 3 support vision?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports 8 k tokens context length.

Other GGUFs of drama-3

Similar models

Browse all →

More Drama models

All Drama →

Other large models

All large models →