Qwen3-TTS 1.7B
A 1.7B-parameter text-to-speech model released by Alibaba's Qwen team, supporting voice cloning and sentence-by-sentence speech synthesis.
Timeline (last 90 days)
Deduplicating the Q/K/V weights saved 488 MiB of VRAM, and keeping the text embedding table on the CPU saved 594 MiB, enabling the two models Gemma 4 E4B and Qwen3-TTS 1.7B to be loaded simultaneously, with the graphics card showing 7,448 MiB used out of 8,188 MiB.
This local voice assistant system is fully self-hosted, with voice detection and recognition running on the CPU, the LLM (Gemma 4 E4B, QAT q4_0 quantization, based on llama.cpp) responsible for generating answers, and the TTS (Qwen3-TTS 1.7B) synthesizing speech sentence by sentence.
All Facts (2)
Deduplicating the Q/K/V weights saved 488 MiB of VRAM, and keeping the text embedding table on the CPU saved 594 MiB, enabling the two models Gemma 4 E4B and Qwen3-TTS 1.7B to be loaded simultaneously, with the graphics card showing 7,448 MiB used out of 8,188 MiB.
50%UnverifiedThis local voice assistant system is fully self-hosted, with voice detection and recognition running on the CPU, the LLM (Gemma 4 E4B, QAT q4_0 quantization, based on llama.cpp) responsible for generating answers, and the TTS (Qwen3-TTS 1.7B) synthesizing speech sentence by sentence.
50%