model_info:
  name: anemll-Qwen3-4B-MLX-dequantized-ctx1024
  version: 0.1.1
  description: |
    Demonstarates running Qwen3-4B on Apple Neural Engine ( alpha release )
    Context length: 1024
    Batch size: 64
    Chunks: 2
  license: MIT
  author: Anemll
  framework: Core ML
  language: Python
  parameters:
    context_length: 1024
    batch_size: 64
    lut_embeddings: none
    lut_ffn: 4
    lut_lmhead: 8
    num_chunks: 2
    model_prefix: qwen
    embeddings: qwen_embeddings.mlmodelc
    lm_head: qwen_lm_head_lut8.mlmodelc
    ffn: qwen_FFN_PF_lut4.mlmodelc
    split_lm_head: 16