Qwen3-TTS-12Hz-1.7B-CustomVoice The memory it needs, what you may do with it, and the hardware it suits.
Short answer. Qwen3-TTS-12Hz-1.7B-CustomVoice needs about 2.6 GB of memory at 4-bit, 3.5 GB at 8-bit and 5.3 GB at full 16-bit precision, including runtime overhead. It has about 1.9 billion parameters. Licence in short: commercial use allowed. By memory alone, on ANVE’s launch configurations: ANVE One fits at BF16, ANVE Office fits at BF16, ANVE Office Pro (GPU) fits at BF16. These are estimates from its published size, not benchmarks.
01
What it is
Qwen3-TTS-12Hz-1.7B-CustomVoice is a text-to-speech model that reads text aloud, published by Alibaba’s Qwen team on Hugging Face on 21 January 2026. It has about 1.9 billion parameters.
Its card lists the licence as Apache 2.0. In short, the licence allows commercial use, modification and redistribution, with attribution and a copy of the licence, and includes a patent grant.
Hugging Face counted about 2,331,704 downloads of it in the 30 days before we checked (7 Oct 2026), and 2,035 people have liked it there.
02
How much memory it needs
The arithmetic: parameters × bits per weight ÷ 8 gives the weights, plus about 1.5 GB for the runtime. These are planning estimates, not measurements.
Speech synthesis also needs working memory for the audio it generates, which is small next to the weights.
Precision
Weights
Total, estimated
BF16 (full precision)
3.8 GB
5.3 GB
8-bit (Q8_0)
2.0 GB
3.5 GB
4-bit (Q4_K)
1.1 GB
2.6 GB
03
Will it fit on ANVE?
Arithmetic against the launch specification, not a test: about three quarters of ANVE One’s 64 GB of unified memory for the model (as AMD’s Variable Graphics Memory allows), and the 24 GB on the graphics card in ANVE Office and ANVE Office Pro, which keep the rest of the stack in 64 GB and 128 GB of system memory. ANVE’s tested default is Qwen 3.8 27B; this model is not yet validated on ANVE.
Configuration (at launch)
Memory for the model
Verdict
ANVE One
about 48 GB of 64 GB unified memory
fits at BF16
ANVE Office
24 GB on the RTX PRO 4000 Blackwell SFF Edition
fits at BF16
ANVE Office Pro (GPU)
24 GB on the RTX PRO 4000 Blackwell
fits at BF16
04
What an office would use it for
For an office, text-to-speech turns a report into an audio briefing. ANVE’s podcast maker writes the script on the box but uses a cloud voice for narration today; local narration is not on ANVE yet.
05
Variants with the same size
Qwen3-TTS-12Hz-1.7B-VoiceDesign: designs a new voice from a text description (same parameter count, so the memory figures above apply).
06
Similar models to compare
VoxCPM2 (2.3B parameters, about 2.8 GB at 4-bit before context; commercial use allowed)
VibeVoice-1.5B (2.7B parameters, about 3.0 GB at 4-bit before context; commercial use allowed)
indic-parler-tts (0.9B parameters, about 2.0 GB at 4-bit before context; commercial use allowed)
07
Questions people ask
How much memory does Qwen3-TTS-12Hz-1.7B-CustomVoice need?
About 2.6 GB at 4-bit, 3.5 GB at 8-bit and 5.3 GB at full 16-bit precision, including about 1.5 GB of runtime overhead. These are estimates from its parameter count.
Can Qwen3-TTS-12Hz-1.7B-CustomVoice run on a 24 GB graphics card?
Yes, at BF16 by this estimate, with room left for context.
Is Qwen3-TTS-12Hz-1.7B-CustomVoice free for commercial use?
Its card lists Apache 2.0, which allows commercial use, modification and redistribution, with attribution and a copy of the licence, and includes a patent grant. Read the licence itself before relying on this summary; it is not legal advice.
08
What is not real yet
No sealed ANVE unit exists; every image of the appliance on this site is a labelled render. The software runs today on a development machine. No customers yet, no certifications, no delivery date, and the final price is not announced.
Reservations are ₹999 in India or US$12 elsewhere, refundable in full until you confirm an order in writing (terms). Offices that cannot use cloud AI can apply to be one of ten design partners.
