Qwen-Qwen3-VL-8B-Thinking-MLX-8bit

johnsmith968530/Qwen-Qwen3-VL-8B-Thinking-MLX-8bit

This model was converted to MLX format from Qwen/Qwen3-VL-8B-Thinking using mlx-vlm version 0.3.7. Refer to the original model card for more details on the model.

export MODEL1_MAJOR="Qwen"
export MODEL1_MINOR="Qwen3-VL-8B-Thinking"
export MODEL1_Q_BITS="8"
export MODEL1_DTS="$(date -z UTC +%Y%m%d_%H%M%SZ)"

echodo () { echo "$@" && "$@"; }
mkdir -p /tmp/mlx/vlm/convert

# uv tool install -U "mlx-vlm[torch]"

echodo time mlx_vlm.convert \
  --hf-path "$MODEL1_MAJOR/$MODEL1_MINOR" \
  --mlx-path "/tmp/mlx/lm/convert/$MODEL1_DTS" \
  --quantize \
  --q-bits "$MODEL1_Q_BITS" \
  --upload-repo \
    "johnsmith968530/$MODEL1_MAJOR-$MODEL1_MINOR-MLX-${MODEL1_Q_BITS}bit"