QW

FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16

QwenGGUF by AMAImediaUpdated 2026-10-29
Download on Hugging Face
Parameters35B
Context—
Layers—
Architectureaudiocpp
Smallest quant23.4 GB
Quick answer

FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 needs about 26.7 GB of memory at Q4_K (a 23.4 GB file) with an 8K context window, so it fits on a 32 GB GPU.

FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 – 35B parameter text‑to‑speech model

FishAudio Drama3 is a 35B parameter TTS model built on the Qwen3.5 architecture. It supports multi‑speaker generation, voice cloning and natural‑language control. The model uses a MoE text backbone with hybrid attention and a Codebook‑MTP audio decoder.

Good at

  • Multi‑character scenes
  • Long‑form content
  • Voice cloning

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is apache‑2.0

Best for

  • Podcast narration
  • Audiobook production
  • Multilingual dubbing

Who it’s for. Developers and content creators needing high‑quality, multi‑speaker TTS. The model is suitable for production environments with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K23.4 GB 26.7 GB
Too big Get file →

The Q4_K quant file is 23.39 GB and needs about 26.7 GB of VRAM at 8 k context. For 8 GB VRAM use a lower‑precision quant if available; otherwise the model will not fit. For 16 GB VRAM the Q4_K quant is the recommended choice.

What GPU do you need for FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K (23.4 GB file, about 26.7 GB in use).

Which FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 quant should you choose?

Q4_K (23.4 GB) is the middle option in this repository. 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

Architectureaudiocpp
Parameters35B

Source

Quantized byAMAImedia
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,298
Last updated2026-10-29

Frequently asked questions about FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16

How much VRAM does FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 need?

About 26.7 GB at Q4_K with an 8K context window. That is the 23.4 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 FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 GGUF?

It depends on the quant: Q4_K is 23.4 GB.

Where can I download FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 GGUF?

The files are on Hugging Face in the AMAImedia/FishAudio-Drama3-TTS-83Lang-Qwen3.5-35B-A3B-FP8-BF16-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 FishAudio Drama3 TTS 83Lang Qwen3.5 35B A3B FP8 BF16 use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

The Q4_K quant requires 26.7 GB VRAM at 8 k context, so it cannot run on 8 GB VRAM.

What license does this model use?

The model is released under the apache‑2.0 license.

Does this model support vision?

No, the model does not support vision.

Other GGUFs of drama-3

Similar models

Browse all →

More from AMAImedia

All by AMAImedia →

More Qwen models

All Qwen →

Other large models

All large models →