Serveurperso / text-to-speech Open weights updated 2 months ago

Qwen3-TTS-GGUF

Name: Qwen3-TTS-GGUF
Author: Serveurperso

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.

Params

—

Context

—

Downloads 30d

1.2 M

Likes

Commercial use: allowed apache-2.0 Not gated GGUF 11 languages View on Hugging Face ↗

Download history

daily snapshots · 89 days

▲ 793 K in the last 30 days (201.0%)

1.2 M317 K

Aug 14Sep 12Oct 12Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
qwen-talker-1.7b-base-Q4_K_M.gguf	Q4_K_M	1.2 GB	1.8 GB	✅ Runs comfortably
qwen-talker-1.7b-base-Q8_0.gguf	Q8_0	2.1 GB	2.8 GB	✅ Runs comfortably
qwen-talker-1.7b-base-F32.gguf	GGUF	7.7 GB	9.0 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence: apache-2.0
First seen on the Hub: 2026-05-11
Training datasets: undisclosed
Added to our catalog: 2026-08-14

Compare with any text-to-speech model

Popular comparisons

Kokoro-82M 12.5 M audio.cpp-gguf 8.9 M XTTS-v2 5.7 M OmniVoice 3.5 M chatterbox 2.4 M VieNeu-TTS-v3-Turbo 2.1 M

Appears in

Best open-source TTS