---
license: apache-2.0
base_models:
- open-r1/OlympicCoder-7B
- Qwen/Qwen2.5-Coder-7B-Instruct
- CodeV-R1-Qwen-7B
- TIGER-Lab/VisCoder-7B
- julien31/Soar-qwen-7b
- Tesslate/Tessa-Rust-T1-7B
- Snowflake/Arctic-Text2SQL-R1-7B
- westenfelder/Qwen2.5-Coder-7B-Instruct-NL2SH
language:
- en
pipeline_tag: text-generation
tags:
- merge
- programming
- code generation
- code
- codeqwen
- moe
- coding
- coder
- qwen2
- chat
- qwen
- qwen-coder
- mixture of experts
- qwen2moe
- 8X7B
- shared expert
- mlx
library_name: mlx
base_model: DavidAU/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B
---

# Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-q8-mlx

This model [Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-q8-mlx](https://huggingface.co/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-q8-mlx) was
converted to MLX format from [DavidAU/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B](https://huggingface.co/DavidAU/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B)
using mlx-lm version **0.26.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-q8-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)
```