Huihui-Qwen3.6-35B-A3B-abliterated-mlx-4bit

Overview

• Format: MLX-VLM
• Precision: 4bit
• Size: 19G
• Source model type: Qwen3_5MoeForConditionalGeneration
• Source pipeline: image-text-to-text
• Intended runtime: mlx-vlm, LM Studio
• Quantization result: 4-bit affine

Validation

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

Notes

Files

• 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-4bit \
  --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-4bit \
  --image /path/to/example.png \
  --prompt "Describe this image." \
  --max-tokens 128 \
  --trust-remote-code \
  --processor-kwargs '{"enable_thinking": false}'