CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit

Date: 2026-11-14Commit: 41d3337Signed: 2DC28CC7B26A283B ✓

Text to speech model with 1.9B parameters. Safetensors weights, 3.08 GB in all. Published by mlx-community under Apache-2.0.

1.9B params3.08GBQwen3-TTS-12Hz-1.7B-CustomVoice-8bitsafetensorspermissive
FactsParams1.9BSize3.08 GBFormatssafetensorsTasktext to speechLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
# manifest sha256 d5f7ab92caf7… · 3.08 GB · 14 files
$ fw verify ./Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
From sourceHosted (signed)mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bitLast check: 2026-11-14 21:30 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of Qwen3-TTS-12Hz-1.7B-CustomVoice.

Works with

Run16Fine-tune7Convert8Scan2
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
3.08 GB
Weights
3.08 GB (safetensors)
Parameters
1.9B
Formats
safetensors
Task
text to speech
License
Apache-2.0 (permissive)
Files
14, each with a sha256
Publisher
mlx-community
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 21:30 UTCpassed

Model card

From the publisher at commit 41d3337. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit#

This model was converted to MLX format from Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice using mlx-audio version 0.3.0.

Refer to the original model card for more details on the model.

Use with mlx-audio#

pip install -U mlx-audio
CLI Example:#
python -m mlx_audio.tts.generate --model mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit --text "Hello, this is a test."
Python Example:#
from mlx_audio.tts.utils import load_model
from mlx_audio.tts.generate import generate_audio

model = load_model("mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

Files

14 files · 3.08 GBWeights 3.08 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.12 KB50fe8f13fc95466beb50a96ae743e40573512754e80330373a043f4bd34d6212
config.json6.06 KB43f29f9ab55cf387bd2ce1d07e9d95a5ca8974fa2fda4e2b45c13ae64aad3bfa
generation_config.json245 Bf1b90b4513f3b34c62851049e2492d7b4c5940daf1276f89c82b8ef04127f3aa
merges.txt1.67 MB599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3
model.safetensors2.39 GBb696f4bf45f54497b6de758981e76f1410bd68af05a657477dee466b0202df1a
model.safetensors.index.json71.8 KB2551ed02dc288b90cd6b7ec98652433f08ef2ae98fb3eda5248a4b9e5b47d08b
preprocessor_config.json127 Befdde1022ea9d76928bf7a9cd53139138f5ba2e466e837f08f6105ab1af1c119
speech_tokenizer/config.json2.34 KBee65bb901c876664ab8707c487157aa1a6ee57c65969b28fb5ec9dc211e68167
speech_tokenizer/configuration.json76 B6bc26d64eb5024b4d1dab5a52371958b429256d6c9d59787f1f5294a54e0cebd
speech_tokenizer/model.safetensors682 MB836b7b357f5ea43e889936a3709af68dfe3751881acefe4ecf0dbd30ba571258
speech_tokenizer/preprocessor_config.json234 Bfcb3805e597e786d4067706e602f6688524640f8d3396790e2e09b5942fcbdfb
tokenizer_config.json7.34 KBdc3c31c3bdaedd5016382bb3cbe07323026775ad51f5a4fb564505992ae4a670
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
41d3337e8b pinned now manifest updated, same commit2026-11-14 21:30 UTC14 files · 3.08 GB
41d3337e8b2026-11-14 21:30 UTC14 files · 3.08 GB

Use it

$ fw get mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
# manifest sha256 d5f7ab92caf7… · 3.08 GB · 14 files
$ fw verify ./Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit.json --dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit $ python3 fw.py verify ./Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit ./mlx-community__Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit --revision 41d3337e8b7f2843a75841595fc14e4b9a7a4b96 --local-dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
50fe8f13fc95466beb50a96ae743e40573512754e80330373a043f4bd34d6212
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject: Qwen3-TTS-12Hz-1.7B-CustomVoice-8bitDate: 2026-11-14Commit: 41d3337Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
Pinned commit
41d3337e8b7f2843a75841595fc14e4b9a7a4b96
Manifest
Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit.json · .minisig
Manifest sha256
d5f7ab92caf7faacc2294ffe995c6f9c0cd85128a4773b54250ba0960a5a03d5
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:30 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit.json.minisig $ minisign -Vm Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF