ModelListadosExterno

Qwen3 TTS GGUF

GGUF weights for qwentts.cpp, a C++17/GGML port of Qwen3-TTS 12 Hz (Qwen team, Alibaba). Multilingual zero shot TTS with named speakers and Mandarin dialects, 24 kHz mono. Runs on CPU, CUDA, Metal, Vulkan.

Fontehuggingface.co/FindaDeath/Qwen3-TTS-GGUF/tree/8a59262e140cb589ade3f36bc7843987ef330b43

TipoOtherModelo baseQwen/Qwen3-TTS-12Hz-0.6B-BaseVersãoRevision 8a59262Bnota

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 243 MB–7,19 GB
Modelo base: Qwen/Qwen3-TTS-12Hz-0.6B-Base
Versão: vRevision 8a59262
Atualizado: 19 de out. de 2026
Downloads: 421
Fonte: Hugging Face

Descrição da fonte

Qwen3-TTS GGUF

Files

Two GGUFs load together :

qwen-talker-{size}-{mode}-{variant}.gguf Qwen3 LM + code predictor MTP head + optional speaker encoder, text -> 12 Hz codes qwen-tokenizer-12hz-{variant}.gguf SEANet + ConvNeXt + DAC v2 + RVQ, 12 Hz codes <-> 24 kHz audio

Three modes are available across two talker sizes :

mode	0.6B	1.7B	use case
base	yes	yes	zero shot TTS with named speakers and dialects
customvoice	yes	yes	zero shot voice cloning from a reference clip
voicedesign	no	yes	voice synthesis from attribute description

The tokenizer is shared across every talker.

variant	talker 0.6B	talker 1.7B	tokenizer	use case
F32	3.7 GB	7.7 GB	647 MB	reference, debug, conversion
BF16	1.8 GB	3.9 GB	359 MB	source faithful, max precision
Q8_0	993 MB	2.1 GB	291 MB	recommended default
Q4_K_M	629 MB	1.2 GB	255 MB	lowest VRAM

Quick start

git clone --recurse-submodules https://github.com/ServeurpersoCom/qwentts.cpp.git
cd qwentts.cpp && ./buildcuda.sh
mkdir -p models
huggingface-cli download Serveurperso/Qwen3-TTS-GGUF \
    qwen-talker-1.7b-base-Q8_0.gguf qwen-tokenizer-12hz-Q8_0.gguf \
    --local-dir models
cd examples
./base.sh         # named speaker      -> base.wav
./clone.sh        # voice cloning      -> clone.wav
./customvoice.sh  # custom voice mode  -> customvoice.wav
./tts.sh          # voice design       -> tts.wav

Backends

Set GGML_BACKEND to force a device, otherwise the runtime picks the best one available.

value	target
`CUDA0`	NVIDIA GPU, fastest path on Ada / Blackwell
`Vulkan0`	Cross vendor GPU (AMD / Intel / NVIDIA)
`Metal`	Apple Silicon GPU
`CPU`	CPU fallback, x86 variant auto selected

Quantization policy

Tokenizer GGUFs are not uniform quants. Three categories get a dedicated treatment :

tensor	dtype across all variants
RVQ codebooks, input_proj / output_proj, speaker encoder fc	F32
1D tensors (gamma, biases, norms, snake alpha and beta)	F32
Conv kernels with non alignable rows (K=7,3,1)	F16 in Q* variants

Conv kernel rows (K=7,3,1) never divide a K-quant block size, so the quantizer skips the Q* intermediates and lands on F16 directly. This is the last resort branch of llama.cpp's tensor_type_fallback applied unconditionally for these kernels. F16 has no block size and matches the runtime target dtype on every backend. The talker LM (Qwen3 backbone, hidden divisible by 256) follows standard llama.cpp K-quant across variants. The code predictor MTP head and the speaker encoder live in the talker GGUF and share its quantization.

License

Upstream model : Qwen3-TTS by Alibaba / Qwen team, Apache 2.0 Audio codec : Qwen3-TTS-Tokenizer-12Hz (Qwen team), Apache 2.0 GGUF tooling : qwentts.cpp, MIT

Fontes

1 fonte

Hugging FacePrimárioVersão 8a59262e140cb589ade3f36bc7843987ef330b43

huggingface.co/FindaDeath/Qwen3-TTS-GGUF/tree/8a59262e140cb589ade3f36bc7843987ef330b43

Verificado 29 de ago.

Artefatos de modelo

24 artefatos

qwen-talker-0.6b-base-BF16.gguf

gguf · 1,72 GB · SHA-256 f0070d96aa4e…29eb · Hugging Face

Baixar

qwen-talker-0.6b-base-F32.gguf

gguf · 3,41 GB · SHA-256 f6a34bfa8b2a…786e · Hugging Face

Baixar

qwen-talker-0.6b-base-Q4_K_M.gguf

gguf · 600 MB · SHA-256 4b468ec7b1f6…4226 · Hugging Face

Baixar

qwen-talker-0.6b-base-Q8_0.gguf

gguf · 947 MB · SHA-256 d54dbaf10591…6426 · Hugging Face

Baixar

qwen-talker-0.6b-customvoice-BF16.gguf

gguf · 1,69 GB · SHA-256 389a153f03e1…8d3e · Hugging Face

Baixar

qwen-talker-0.6b-customvoice-F32.gguf

gguf · 3,38 GB · SHA-256 436d1f130ee8…4f37 · Hugging Face

Baixar

qwen-talker-0.6b-customvoice-Q4_K_M.gguf

gguf · 577 MB · SHA-256 b3a7e6613d80…8e1e · Hugging Face

Baixar

qwen-talker-0.6b-customvoice-Q8_0.gguf

gguf · 924 MB · SHA-256 4eb38675c736…8519 · Hugging Face

Baixar

qwen-talker-1.7b-base-BF16.gguf

gguf · 3,61 GB · SHA-256 7f4567113f3a…ffa5 · Hugging Face

Baixar

qwen-talker-1.7b-base-F32.gguf

gguf · 7,19 GB · SHA-256 7f563aa562e6…528a · Hugging Face

Baixar

qwen-talker-1.7b-base-Q4_K_M.gguf

gguf · 1,14 GB · SHA-256 ea393ebaf216…887d · Hugging Face

Baixar

qwen-talker-1.7b-base-Q8_0.gguf

gguf · 1,94 GB · SHA-256 4b9a33a23690…4fda · Hugging Face

Baixar

qwen-talker-1.7b-customvoice-BF16.gguf

gguf · 3,58 GB · SHA-256 dd5d70d3f7d0…276c · Hugging Face

Baixar

qwen-talker-1.7b-customvoice-F32.gguf

gguf · 7,15 GB · SHA-256 f7df5b2be1d8…251b · Hugging Face

Baixar

qwen-talker-1.7b-customvoice-Q4_K_M.gguf

gguf · 1,10 GB · SHA-256 cc328834a631…fc4a · Hugging Face

Baixar

qwen-talker-1.7b-customvoice-Q8_0.gguf

gguf · 1,90 GB · SHA-256 cab2cff67a0a…89fa · Hugging Face

Baixar

qwen-talker-1.7b-voicedesign-BF16.gguf

gguf · 3,58 GB · SHA-256 f389939fed3c…ad42 · Hugging Face

Baixar

qwen-talker-1.7b-voicedesign-F32.gguf

gguf · 7,15 GB · SHA-256 b32c8571977f…ee90 · Hugging Face

Baixar

qwen-talker-1.7b-voicedesign-Q4_K_M.gguf

gguf · 1,10 GB · SHA-256 7605ed0cc5e7…eee3 · Hugging Face

Baixar

qwen-talker-1.7b-voicedesign-Q8_0.gguf

gguf · 1,90 GB · SHA-256 575610ab1ddc…2276 · Hugging Face

Baixar

qwen-tokenizer-12hz-BF16.gguf

gguf · 342 MB · SHA-256 cc04d7352ff4…fa18 · Hugging Face

Baixar

qwen-tokenizer-12hz-F32.gguf

gguf · 617 MB · SHA-256 b16b95557c7c…5f3d · Hugging Face

Baixar

qwen-tokenizer-12hz-Q4_K_M.gguf

gguf · 243 MB · SHA-256 cf3788b4d50a…8039 · Hugging Face

Baixar

qwen-tokenizer-12hz-Q8_0.gguf

gguf · 278 MB · SHA-256 1883beeed993…fd94 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme29 de ago.huggingface.co/FindaDeath/Qwen3-TTS-GGUF

--- license: apache-2.0 library_name: gguf pipeline_tag: text-to-speech tags: - tts - text-to-speech - voice-cloning - voice-design - mandarin-dialects - ggml - gguf - qwen - qwen3 - qwen3-tts - cpp language: - zh - en - fr - de - es - it - pt - ja - ko - ru - ar base_model: - Qwen/Qwen3-TTS-Tokenizer-12Hz - Qwen/Qwen3-TTS-12Hz-0.6B-Base - Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice - Qwen/Qwen3-TTS-12Hz-1.7B-Base - Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice - Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --- # Qwen3-TTS GGUF GGUF weights for [qwentts.cpp](https://github.com/ServeurpersoCom/qwentts.cpp), a C++17/GGML port of Qwen3-TTS 12 Hz (Qwen team, Alibaba). Multilingual zero shot TTS with named speakers and Mandarin dialects, 24 kHz mono. Runs on CPU, CUDA, Metal, Vulkan. ## Files Two GGUFs load together : qwen-talker-{size}-{mode}-{variant}.gguf Qwen3 LM + code predictor MTP head + optional speaker encoder, text -> 12 Hz codes qwen-tokenizer-12hz-{variant}.gguf SEANet + ConvNeXt + DAC v2 + RVQ, 12 Hz codes <-> 24 kHz audio Three modes are available across two talker sizes : | mode | 0.6B | 1.7B | use case | |-------------|------|------|---------------------------------------------------| | base | yes | yes | zero shot TTS with named speakers and dialects | | customvoice | yes | yes | zero shot voice cloning from a reference clip | | voicedesign | no | yes | voice synthesis from attribute description | The tokenizer is shared across every talker. | variant | talker 0.6B | talker 1.7B | tokenizer | use case | |---------|-------------|-------------|-----------|--------------------------------| | F32 | 3.7 GB | 7.7 GB | 647 MB | reference, debug, conversion | | BF16 | 1.8 GB | 3.9 GB | 359 MB | source faithful, max precision | | Q8_0 | 993 MB | 2.1 GB | 291 MB | recommended default | | Q4_K_M | 629 MB | 1.2 GB | 255 MB | lowest VRAM | ## Quick start ``` git clone --recurse-submodules https://github.com/ServeurpersoCom/qwentts.cpp.git cd qwentts.cpp && ./buildcuda.sh mkdir -p models huggingface-cli download Serveurperso/Qwen3-TTS-GGUF \ qwen-talker-1.7b-base-Q8_0.gguf qwen-tokenizer-12hz-Q8_0.gguf \ --local-dir models cd examples ./base.sh # named speaker -> base.wav ./clone.sh # voice cloning -> clone.wav ./customvoice.sh # custom voice mode -> customvoice.wav ./tts.sh # voice design -> tts.wav ``` ## Backends Set `GGML_BACKEND` t...

Note29 de ago.huggingface.co/FindaDeath/Qwen3-TTS-GGUF

Source context: 421 downloads · 1 likes · Pipeline text-to-speech · Library gguf · Repo FindaDeath/Qwen3-TTS-GGUF