---
license: apache-2.0
language:
- zh
- en
- de
- es
- fr
- ja
- it
- he
- ko
- ru
- fa
- ar
- pl
- pt
- cs
- da
- sv
- hu
- el
- tr
tags:
- gguf
- tts
- text-to-speech
- moss-tts
base_model: OpenMOSS-Team/MOSS-TTS-Nano
---

# MOSS-TTS-Nano GGUF (codec only)

GGUF conversion of the **MOSS-Audio-Tokenizer-Nano** codec used by [`OpenMOSS-Team/MOSS-TTS-Nano`](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano), runnable via [codec.cpp](https://github.com/mybigday/codec.cpp).

> ⚠️ **The LLM-part is not converted yet** — see [Status](#status).

## Files

### Codec-part (MOSS-Audio-Tokenizer-Nano, `moss_audio` arch, 16 RVQ codebooks × 1024, 48 kHz stereo)

`codec[-<quant>].gguf`

| File                | Size   |
| ------------------- | ------ |
| `codec-f32.gguf`    | 84 MB  |
| `codec-f16.gguf`    | 42 MB  |
| `codec-q8_0.gguf`   | 24 MB  |
| `codec-q5_k_m.gguf` | 17 MB  |
| `codec-q4_k_m.gguf` | 15 MB  |

## Status

The MOSS-TTS-Nano LLM-part is a **custom `MossTTSNanoForCausalLM` architecture** that stock llama.cpp doesn't load:

- **GPT-2 backbone with RoPE** (`position_embedding_type: "rope"`, `rope_base: 10000`) — llama.cpp's `gpt2` arch only handles learned absolute positions, not RoPE
- **16 RVQ codebooks** (1024 entries each) emitted per audio frame
- **Global + local transformer**: the GPT-2 global produces a hidden state per timestep and a 1-layer local transformer expands it into the 16 codebook predictions

A working LLM-part GGUF would need a custom `moss_tts_nano` architecture inside llama.cpp (model loader, graph builder for global + local transformer, multi-codebook output handling). That's substantial work — comparable to or larger than implementing Chatterbox-T3.

For now this repo only ships the codec; the LLM-part will follow if/when the architecture lands in llama.cpp.

## Notes

- Source weights: [`OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano`](https://huggingface.co/OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano)
- Full upstream Python pipeline: [`OpenMOSS-Team/MOSS-TTS-Nano`](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano)