---
title: Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx
canonical_url: "https://www.modelscope.cn/models/nightmedia/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx"
md_url: "https://www.modelscope.cn/models/nightmedia/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx.md"
repository: nightmedia/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx
last_updated: 2025-09-22
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_moe
architectures:
  - Qwen3MoeForCausalLM
base_model:
  - YOYO-AI/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507
base_model_relation: quantized
parameters: 9.5B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 19
stars: 0
tags:
  - merge
  - mlx
---

# Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx

> Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx - nightmedia 在 ModelScope 开源的模型。Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx

nightmedia/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx 是 ModelScope 魔搭社区上的 9.5B 参数text-generation模型，采用 apache-2.0 许可，基于 YOYO-AI/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: nightmedia/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 9.5B
- **Base model**: YOYO-AI/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: merge, mlx
- **Downloads**: 19
- **Stars**: 0
- **Last updated**: 2025-09-22

Source: https://www.modelscope.cn/models/nightmedia/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx

---

# Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx

This model [Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx](https://huggingface.co/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx) was
converted to MLX format from [YOYO-AI/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507](https://huggingface.co/YOYO-AI/Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507)
using mlx-lm version **0.28.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Qwen3-30B-A3B-Deepseek-Distill-Instruct-2507-q8-hi-mlx")

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)
```