---
title: IQuest-Coder-V1-7B-Thinking-mlx_8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit.md"
repository: mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit
last_updated: 2026-03-04
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - iquestcoder
architectures:
  - IQuestCoderForCausalLM
base_model:
  - IQuestLab/IQuest-Coder-V1-7B-Thinking
base_model_relation: quantized
parameters: 2.1B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 11
stars: 0
tags:
  - mlx
---

# IQuest-Coder-V1-7B-Thinking-mlx_8bit

> IQuest-Coder-V1-7B-Thinking-mlx_8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/IQuest-Coder-V1-7B-Thinking-mlx8bit

mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit 是 ModelScope 魔搭社区上的 2.1B 参数text-generation模型，采用 other 许可，基于 IQuestLab/IQuest-Coder-V1-7B-Thinking 构建。

- **Repository**: mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 2.1B
- **Base model**: IQuestLab/IQuest-Coder-V1-7B-Thinking
- **Tags**: mlx
- **Downloads**: 11
- **Stars**: 0
- **Last updated**: 2026-03-04

Source: https://www.modelscope.cn/models/mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit

---

# mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit

This model [mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit](https://huggingface.co/mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_8bit) was
converted to MLX format from [IQuestLab/IQuest-Coder-V1-7B-Thinking](https://huggingface.co/IQuestLab/IQuest-Coder-V1-7B-Thinking)
using mlx-lm version **0.30.7**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/IQuest-Coder-V1-7B-Thinking-mlx_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, return_dict=False,
    )

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