---
library_name: mlx-vlm
pipeline_tag: image-text-to-text
base_model: huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated

tags:
- mlx
- mlx-vlm
- qwen3.6
- multimodal
- vision-language
- lm-studio
- abliterated
---

# Huihui-Qwen3.6-35B-A3B-abliterated-mlx-bf16

MLX-VLM conversion of [huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated).

## Overview

- Format: MLX-VLM
- Precision: bf16
- Size: 66G
- Source model type: Qwen3_5MoeForConditionalGeneration
- Source pipeline: image-text-to-text
- Intended runtime: mlx-vlm, LM Studio


## Validation

Local checks on Apple Silicon:

- model loading in mlx-vlm: passed
- text generation smoke test: passed
- image generation path smoke test: passed

Smoke-test logs were produced locally before upload.

## Notes

This is an abliterated model conversion. Outputs may be less filtered than standard instruction-tuned models. Use responsibly and comply with applicable laws and platform policies.

## Files

Important files in this repo:

- config.json
- generation_config.json
- chat_template.jinja
- tokenizer.json
- tokenizer_config.json
- model.safetensors.index.json
- model-*.safetensors

## Usage

### Text generation

    mlx_vlm.generate \
      --model /path/to/Huihui-Qwen3.6-35B-A3B-abliterated-mlx-bf16 \
      --prompt "你好" \
      --max-tokens 128 \
      --trust-remote-code \
      --processor-kwargs '{"enable_thinking": false}'

### Image prompt

    mlx_vlm.generate \
      --model /path/to/Huihui-Qwen3.6-35B-A3B-abliterated-mlx-bf16 \
      --image /path/to/example.png \
      --prompt "Describe this image." \
      --max-tokens 128 \
      --trust-remote-code \
      --processor-kwargs '{"enable_thinking": false}'