---
title: MiroThinker-1.7-mini-mlx-4Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/MiroThinker-1.7-mini-mlx-4Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/MiroThinker-1.7-mini-mlx-4Bit.md"
repository: mlx-community/MiroThinker-1.7-mini-mlx-4Bit
last_updated: 2026-03-16
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_moe
architectures:
  - Qwen3MoeForCausalLM
base_model:
  - miromind-ai/MiroThinker-1.7-mini
base_model_relation: quantized
parameters: 4.8B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 43
stars: 0
tags:
  - agent
  - open-source
  - miromind
  - deep-research
  - mlx
  - mlx-my-repo
---

# MiroThinker-1.7-mini-mlx-4Bit

> MiroThinker-1.7-mini-mlx-4Bit - mlx-community 在 ModelScope 开源的模型。cbalgeman/MiroThinker-1.7-mini-mlx-4Bit

mlx-community/MiroThinker-1.7-mini-mlx-4Bit 是 ModelScope 魔搭社区上的 4.8B 参数text-generation模型，采用 apache-2.0 许可，基于 miromind-ai/MiroThinker-1.7-mini 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/MiroThinker-1.7-mini-mlx-4Bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 4.8B
- **Base model**: miromind-ai/MiroThinker-1.7-mini
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: agent, open-source, miromind, deep-research, mlx, mlx-my-repo
- **Downloads**: 43
- **Stars**: 0
- **Last updated**: 2026-03-16

Source: https://www.modelscope.cn/models/mlx-community/MiroThinker-1.7-mini-mlx-4Bit

---

# cbalgeman/MiroThinker-1.7-mini-mlx-4Bit

The Model [cbalgeman/MiroThinker-1.7-mini-mlx-4Bit](https://huggingface.co/cbalgeman/MiroThinker-1.7-mini-mlx-4Bit) was converted to MLX format from [miromind-ai/MiroThinker-1.7-mini](https://huggingface.co/miromind-ai/MiroThinker-1.7-mini) using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("cbalgeman/MiroThinker-1.7-mini-mlx-4Bit")

prompt="hello"

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

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