---
title: QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit.md"
repository: mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit
last_updated: 2025-03-15
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
parameters: 5.1B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 825
stars: 1
tags:
  - mergekit
  - merge
  - mlx
  - mlx-my-repo
---

# QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit

> QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit - mlx-community 在 ModelScope 开源的模型。sm54's best merge, useful, practical, I like it!

mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit 是 ModelScope 魔搭社区上的 5.1B 参数text-generation模型，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit
- **Tasks**: text-generation
- **Parameters**: 5.1B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mergekit, merge, mlx, mlx-my-repo
- **Downloads**: 825
- **Stars**: 1
- **Last updated**: 2025-03-15

Source: https://www.modelscope.cn/models/mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit

---

sm54's best merge, useful, practical, I like it! 

Faster than QwQ, better coding than Gemma3 and less censored.

Simple censor test prompt: "George Carlins 7 dirty words"


# bobig/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit

The Model [bobig/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit](https://huggingface.co/bobig/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit) was converted to MLX format from [sm54/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B](https://huggingface.co/sm54/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B) using mlx-lm version **0.21.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("bobig/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-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)
```