---
title: orpheus-3b-0.1-ft-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/orpheus-3b-0.1-ft-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/orpheus-3b-0.1-ft-8bit.md"
repository: mlx-community/orpheus-3b-0.1-ft-8bit
last_updated: 2025-03-21
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - canopylabs/orpheus-3b-0.1-ft
base_model_relation: quantized
parameters: 928.5M
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 511
stars: 1
tags:
  - mlx
---

# orpheus-3b-0.1-ft-8bit

> orpheus-3b-0.1-ft-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/orpheus-3b-0.1-ft-8bit

mlx-community/orpheus-3b-0.1-ft-8bit 是 ModelScope 魔搭社区上的 928.5M 参数text-to-speech模型，采用 apache-2.0 许可，基于 canopylabs/orpheus-3b-0.1-ft 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/orpheus-3b-0.1-ft-8bit
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 928.5M
- **Base model**: canopylabs/orpheus-3b-0.1-ft
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 511
- **Stars**: 1
- **Last updated**: 2025-03-21

Source: https://www.modelscope.cn/models/mlx-community/orpheus-3b-0.1-ft-8bit

---

# mlx-community/orpheus-3b-0.1-ft-8bit

This model [mlx-community/orpheus-3b-0.1-ft-8bit](https://huggingface.co/mlx-community/orpheus-3b-0.1-ft-8bit) was
converted to MLX format from [canopylabs/orpheus-3b-0.1-ft](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft)
using mlx-audio version **0.0.3**.

## Use with mlx

```bash
pip install -U mlx-audio
```

```bash
python -m mlx_audio.tts.generate --model mlx-community/orpheus-3b-0.1-ft-8bit --text "Hello world" --voice tara --temperature 0.6 --audio_format mp3```