MI

miotts 0.6b

MiocodecGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters600M
Context—
Layers—
Architecturemio-embedding
Smallest quant0.0 GB
Quick answer

miotts 0.6b needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.0 GB to 1.4 GB (F16).

Miotts 0.6b – 44.1 kHz audio codec with Qwen3 LLM

Miotts 0.6b is a GGUF model combining a 28‑layer Qwen3 LLM and the MioCodec‑25Hz‑44.1kHz‑v2 waveform decoder. It outputs 44.1 kHz mono PCM and requires a voice preset for intelligible audio. The model is licensed under Apache‑2.0.

Good at

  • High‑fidelity 44.1 kHz audio generation
  • Zero‑shot voice conversion
  • Integration with Qwen3 LLM for TTS

Limits

  • No vision support
  • Requires voice preset for quality
  • Context length not specified

Best for

  • TTS pipelines needing 44.1 kHz output
  • Voice conversion tasks
  • ASR roundtrip with CrispASR

Who it’s for. Developers building text‑to‑speech or voice conversion systems that need high‑fidelity audio. The model is suitable for applications where a 44.1 kHz codec is required and the user can supply a voice preset.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
Q4_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.8 GB 1.4 GB
Fits Get file →
F161.4 GB 2.1 GB
Fits Get file →

For 8 GB VRAM use Q4_K (0.53 GB file, ~1.1 GB memory at 8k context). For 12 GB VRAM use Q8_0 (0.83 GB file, ~1.4 GB memory). For 16 GB VRAM use F16 (1.4 GB file, ~2.1 GB memory). Memory estimates are approximate.

What GPU do you need for miotts 0.6b?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (1.4 GB file, about 2.1 GB in use).

Which miotts 0.6b quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemio-embedding
Parameters600M

Source

Quantized bycstr
FamilyMiocodec
Licenseapache-2.0
Downloads (HF)724
Last updated2026-08-02

Frequently asked questions about miotts 0.6b

How much VRAM does miotts 0.6b need?

About 0.5 GB at its main file with an 8K context window. That is the 0.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run miotts 0.6b on an 8 GB GPU?

Yes, with F16: the 1.4 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of miotts 0.6b GGUF?

It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, Q4_K is 0.5 GB, Q8_0 is 0.8 GB and 1 more.

Where can I download miotts 0.6b GGUF?

The files are on Hugging Face in the cstr/miotts-0.6b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does miotts 0.6b use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Miotts 0.6b on 8 GB VRAM?

Yes, the Q4_K quantization requires about 1.1 GB of VRAM at 8k context, which fits within 8 GB.

Does Miotts 0.6b support vision tasks?

No, the model has no vision capabilities.

Do I need a voice preset to use Miotts 0.6b?

Yes, a voice preset is required for intelligible audio output.

Other GGUFs of MioCodec-25Hz-44.1kHz-v2

Similar models

Browse all →

More from cstr

All by cstr →

More Miocodec models

All Miocodec →

Other tiny models

All tiny models →