---
title: Kimi-Linear-48B-A3B-Instruct-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit.md"
repository: mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit
last_updated: 2026-01-23
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - kimi_linear
architectures:
  - KimiLinearForCausalLM
base_model:
  - moonshotai/Kimi-Linear-48B-A3B-Instruct
base_model_relation: quantized
parameters: 6.1B
tensor_type:
  - U32
  - BF16
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 79
stars: 0
tags:
  - mlx
---

# Kimi-Linear-48B-A3B-Instruct-3bit

> Kimi-Linear-48B-A3B-Instruct-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit

mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit 是 ModelScope 魔搭社区上的 6.1B 参数text-generation模型，采用 mit 许可，基于 moonshotai/Kimi-Linear-48B-A3B-Instruct 构建。

- **Repository**: mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 6.1B
- **Base model**: moonshotai/Kimi-Linear-48B-A3B-Instruct
- **Tags**: mlx
- **Downloads**: 79
- **Stars**: 0
- **Last updated**: 2026-01-23

Source: https://www.modelscope.cn/models/mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit

---

# mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit

This model [mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit](https://huggingface.co/mlx-community/Kimi-Linear-48B-A3B-Instruct-3bit) was
converted to MLX format from [moonshotai/Kimi-Linear-48B-A3B-Instruct](https://huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct)
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/Kimi-Linear-48B-A3B-Instruct-3bit")

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)
```