Qwen

Qwen3-TTS-12Hz-1.7B-Base

Name: Qwen3-TTS-12Hz-1.7B-Base
Author: Qwen

← All models

1.9B parameters · Base · Qwen3 family

apache-2.0 source matched revision pinned

Nothing to download yet — not yet mirrored

We haven't mirrored a torrent for this model yet. The metadata is cataloged, but no downloadable build exists here right now.

Request this model on the board

Which version should I download?

Default pick: safetensors · BF16 — BF16 source weights (official Qwen3-TTS-12Hz-1.7B-Base) — reference TTS artifact. GGUF community-only; safetensors is the universal format (Transformers/vLLM). Bundles speech_tokenizer codec (+682MB) + tokenizer/config.

Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.

Set your rig

Quantizations

Why these quants? Which quant should I pick?

Format	Level	Size	Verdict	Est. speed	Quality note	Swarm	Download
safetensors	BF16	3.59 GB	Set your rig	—	BF16 source weights (official Qwen3-TTS-12Hz-1.7B-Base) — reference TTS artifact. GGUF community-only; safetensors is the universal format (Transformers/vLLM). Bundles speech_tokenizer codec (+682MB) + tokenizer/config.	—	Not yet available

safetensors · BF16

3.59 GB

Set your rig

Est. speed: —
Swarm: —

BF16 source weights (official Qwen3-TTS-12Hz-1.7B-Base) — reference TTS artifact. GGUF community-only; safetensors is the universal format (Transformers/vLLM). Bundles speech_tokenizer codec (+682MB) + tokenizer/config.

Not yet available

Run it

Quant

Context / KV 8,192 tokens · FP16 set above the quant table

Generic commands (no rig set). GPU-offload values assume the model fits on your GPU — set your rig for values tuned to your hardware.

Start the server

llama-server -m qwen-qwen3-tts-12hz-1-7b-base-BF16.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt.

Save as Modelfile next to the GGUF (Modelfile)

FROM ./qwen-qwen3-tts-12hz-1-7b-base-BF16.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999

Create

ollama create qwen-qwen3-tts-12hz-1-7b-base -f Modelfile

Run

ollama run qwen-qwen3-tts-12hz-1-7b-base

Serve an OpenAI-compatible endpoint

vllm serve Qwen/Qwen3-TTS-12Hz-1.7B-Base --max-model-len 8192

Serves on http://localhost:8000/v1 by default.

Load qwen-qwen3-tts-12hz-1-7b-base-BF16.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).

Not an MLX-format quant.

MLX runs MLX-format weights only (Apple Silicon). This quant is not an MLX build.

Filename shown is a placeholder. The exact GGUF name appears once the download is available.

Technical details

No template or sampling metadata recorded.

Evidence & provenance

Source

Provenance: https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base
Revision pin: fd4b254389122332181a7c3db7f27e918eec64e3
Manifest: None

License

Name: apache-2.0
Commercial use: yes
Access: Open

File hashes (SHA-256)

No file hashes recorded yet.

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard

Reviews & presets

Reviews (0)

No reviews yet.

Sampler presets

No presets yet.

Community runtime reports

Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.

No community reports yet.