SAVRN
Search Contact SAVRN

Open-weight model

Qwen3-TTS-12Hz-1.7B-Base

by Qwen Qwen/Qwen3-TTS-12Hz-1.7B-Base

Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs.

Parameters1.9B
Context
Weights4.5 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads3.8M

Runs On

What it takes to serve Qwen3-TTS-12Hz-1.7B-Base (1.9B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 3.9 GB 4.6 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 1.9 GB 2.3 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.0 GB 1.2 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on Qwen3-TTS-12Hz-1.7B-Base

The name says 1.7B and the configuration counts 1,928,677,440 parameters, so budget for 1.9B. That puts 16-bit memory at 4.6 GB for 3.9 GB of weights and 8-bit at 2.3 GB, both a sliver of the cheapest setup we list, one MI300X with 192 GB at $1.85 an hour. Its purpose is speech generation across ten languages, Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish and Italian, with dialect voice profiles and control of tone, speaking rate and emotion from natural-language instructions.

Deploying it commercially is allowed; Apache 2.0 covers modification and redistribution too, as long as the license and NOTICE file stay and significant changes are stated. Check the empty library field. Nothing in the record says which serving stack loads Qwen3TTSForConditionalGeneration, so prove that before you buy time. Then read the technical report, arXiv:2601.15621, for what the Base suffix means against the instruction-driven control described here.

Model Card

By Qwen, published under apache-2.0, revision fd4b25438912.

Qwen3-TTS

Overview

Introduction

Read the full model card (3,390 words)

Configuration

Architecture
Qwen3TTSForConditionalGeneration
Model type
qwen3_tts

Identity and Version

Repository
Qwen/Qwen3-TTS-12Hz-1.7B-Base
Publisher
Qwen
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
1.9B parameters
Languages
Not stated by the source
Revision
fd4b254389122332181a7c3db7f27e918eec64e3
First published
2026-01-21
Last updated
2026-01-23

Files and Weights

13 files, 4.5 GB in total. The weights are 2 files totalling 4.5 GB in safetensors.

Weights2 files · 4.5 GB
Configuration6 files · 7.5 KB
Tokenizer3 files · 4.5 MB
Documentation1 file · 57.8 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights3.9 GB 38fc7fc51c5e
speech_tokenizer/model.safetensorsWeights682.3 MB 836b7b357f5e
config.jsonConfiguration4.5 KB
generation_config.jsonConfiguration245 B
preprocessor_config.jsonConfiguration127 B
speech_tokenizer/config.jsonConfiguration2.3 KB
speech_tokenizer/configuration.jsonConfiguration76 B
speech_tokenizer/preprocessor_config.jsonConfiguration234 B
README.mdDocumentation57.8 KB
.gitattributesRepository1.5 KB
merges.txtTokenizer1.7 MB
tokenizer_config.jsonTokenizer7.3 KB
vocab.jsonTokenizer2.8 MB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
4.5 GB
Download from Qwen

Released by Qwen through ModelScope. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published4.5 GB
16-bit3.9 GB
8-bit1.9 GB
4-bit1.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Built on This Model

Questions About Qwen3-TTS-12Hz-1.7B-Base

How much GPU memory does Qwen3-TTS-12Hz-1.7B-Base need?

About 4.6 GB at 16-bit and 1.2 GB at 4-bit: the weights (1.9B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen3-TTS-12Hz-1.7B-Base on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use Qwen3-TTS-12Hz-1.7B-Base commercially?

Yes. Qwen3-TTS-12Hz-1.7B-Base is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.