---
title: RakutenAI-7B-chat-MLX-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/RakutenAI-7B-chat-MLX-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/RakutenAI-7B-chat-MLX-4bit.md"
repository: mlx-community/RakutenAI-7B-chat-MLX-4bit
last_updated: 2026-03-20
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral
architectures:
  - MistralForCausalLM
base_model:
  - Rakuten/RakutenAI-7B-chat
base_model_relation: quantized
parameters: 1.2B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ja
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 8
stars: 0
tags:
  - mlx
---

# RakutenAI-7B-chat-MLX-4bit

> RakutenAI-7B-chat-MLX-4bit - mlx-community 在 ModelScope 开源的模型。This model was converted to MLX format from Rakuten/RakutenAI-7B-chat using mlx-lm version 0.31.0. Refer to the original model card for more details on the model.

mlx-community/RakutenAI-7B-chat-MLX-4bit 是 ModelScope 魔搭社区上的 1.2B 参数text-generation模型，基于 Rakuten/RakutenAI-7B-chat 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/RakutenAI-7B-chat-MLX-4bit
- **Tasks**: text-generation
- **Parameters**: 1.2B
- **Base model**: Rakuten/RakutenAI-7B-chat
- **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**: 8
- **Stars**: 0
- **Last updated**: 2026-03-20

Source: https://www.modelscope.cn/models/mlx-community/RakutenAI-7B-chat-MLX-4bit

---

This model was converted to MLX format from [`Rakuten/RakutenAI-7B-chat`](https://huggingface.co/Rakuten/RakutenAI-7B-chat) using mlx-lm version **0.31.0**.
Refer to the [original model card](https://huggingface.co/Rakuten/RakutenAI-7B-chat) for more details on the model.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/RakutenAI-7B-chat-MLX-4bit")

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)
```

```
Inference: M3 Ultra
RakutenAI-2.0-mini-MLX-4bit
==========
Hello there, how can I help you today?
==========
Prompt: 38 tokens, 174.003 tokens-per-sec
Generation: 11 tokens, 141.866 tokens-per-sec
Peak memory: 4.256 GB

```