---
title: Ring-flash-linear-2.0-128k-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Ring-flash-linear-2.0-128k-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Ring-flash-linear-2.0-128k-8bit.md"
repository: mlx-community/Ring-flash-linear-2.0-128k-8bit
last_updated: 2025-11-03
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - bailing_moe_linear
architectures:
  - BailingMoeLinearV2ForCausalLM
base_model:
  - inclusionAI/Ring-flash-linear-2.0-128k
base_model_relation: quantized
parameters: 29.3B
tensor_type:
  - U32
  - F32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 59
stars: 0
tags:
  - moe
  - mlx
---

# Ring-flash-linear-2.0-128k-8bit

> Ring-flash-linear-2.0-128k-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Ring-flash-linear-2.0-128k-8bit

mlx-community/Ring-flash-linear-2.0-128k-8bit 是 ModelScope 魔搭社区上的 29.3B 参数text-generation模型，采用 mit 许可，基于 inclusionAI/Ring-flash-linear-2.0-128k 构建。

- **Repository**: mlx-community/Ring-flash-linear-2.0-128k-8bit
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 29.3B
- **Base model**: inclusionAI/Ring-flash-linear-2.0-128k
- **Tags**: moe, mlx
- **Downloads**: 59
- **Stars**: 0
- **Last updated**: 2025-11-03

Source: https://www.modelscope.cn/models/mlx-community/Ring-flash-linear-2.0-128k-8bit

---

# mlx-community/Ring-flash-linear-2.0-128k-8bit

This model [mlx-community/Ring-flash-linear-2.0-128k-8bit](https://huggingface.co/mlx-community/Ring-flash-linear-2.0-128k-8bit) was
converted to MLX format from [inclusionAI/Ring-flash-linear-2.0-128k](https://huggingface.co/inclusionAI/Ring-flash-linear-2.0-128k)
using mlx-lm version **0.28.4**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Ring-flash-linear-2.0-128k-8bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```