---
library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model: Qwen/Qwen3.5-35B-A3B
tags:
- mlx
- qwen3.5
- moe
- 2bit
- quantized
---

# Qwen3.5-35B-A3B-MLX-2bit

This is a **MLX Q2** quantized *(2.504 average bits per parameter)* version of [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B), aiming to fit on 16GB Unified Memory.

*Quantized with [mlx-lm](https://github.com/ml-explore/mlx-lm)*

## Usage

```python
from mlx_lm import load, generate

model, tokenizer = load("MercuriusDream/Qwen3.5-35B-A3B-MLX-2bit")
messages = [{"role": "user", "content": "Hello!"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
text = generate(model, tokenizer, prompt=prompt, verbose=True)
```