---
title: Qwen2.5-Coder-1.5B-Instruct-Q6
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen2.5-Coder-1.5B-Instruct-Q6"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen2.5-Coder-1.5B-Instruct-Q6.md"
repository: mlx-community/Qwen2.5-Coder-1.5B-Instruct-Q6
last_updated: 2025-02-18
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Qwen/Qwen2.5-Coder-1.5B-Instruct
base_model_relation: quantized
parameters: 337.8M
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 657
stars: 0
tags:
  - code
  - codeqwen
  - chat
  - qwen
  - qwen-coder
  - mlx
---

# Qwen2.5-Coder-1.5B-Instruct-Q6

> Qwen2.5-Coder-1.5B-Instruct-Q6 - mlx-community 在 ModelScope 开源的模型。bobig/Qwen2.5-Coder-1.5B-Instruct-Q6

mlx-community/Qwen2.5-Coder-1.5B-Instruct-Q6 是 ModelScope 魔搭社区上的 337.8M 参数text-generation模型，采用 apache-2.0 许可，基于 Qwen/Qwen2.5-Coder-1.5B-Instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Qwen2.5-Coder-1.5B-Instruct-Q6
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 337.8M
- **Base model**: Qwen/Qwen2.5-Coder-1.5B-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: code, codeqwen, chat, qwen, qwen-coder, mlx
- **Downloads**: 657
- **Stars**: 0
- **Last updated**: 2025-02-18

Source: https://www.modelscope.cn/models/mlx-community/Qwen2.5-Coder-1.5B-Instruct-Q6

---

# bobig/Qwen2.5-Coder-1.5B-Instruct-Q6


This works well as a draft model for speculative decoding in [LMstudio 3.10 beta](https://lmstudio.ai/docs/advanced/speculative-decoding)

Try it with: [mlx-community/Qwen2.5-14B-1M-YOYO-V2-Q4](https://huggingface.co/mlx-community/Qwen2.5-14B-1M-YOYO-V2-Q4)

you should see about 50% faster TPS for math/code prompts. For a quick test try: "count backwards from 100 to 1"

Q4 was a little too dumb, Q8 was a little too slow...so Q6 


The Model [bobig/Qwen2.5-Coder-1.5B-Instruct-Q6](https://huggingface.co/bobig/Qwen2.5-Coder-1.5B-Instruct-Q6) was
converted to MLX format from [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)
using mlx-lm version **0.21.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("bobig/Qwen2.5-Coder-1.5B-Instruct-Q6")

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)
```