model_info:
  name: anemll-qwen3_0.6b_model_original-ctx4096
  version: 0.3.4
  description: |
    Demonstarates running qwen3_0.6b_model_original on Apple Neural Engine
    Context length: 4096
    Batch size: 64
    Chunks: 1
  license: MIT
  author: Anemll
  framework: Core ML
  language: Python
  architecture: qwen3
  parameters:
    context_length: 4096
    batch_size: 64
    lut_embeddings: none
    lut_ffn: 8
    lut_lmhead: 8
    num_chunks: 1
    model_prefix: qwen
    embeddings: qwen_embeddings.mlmodelc
    lm_head: qwen_lm_head_lut8.mlmodelc
    ffn: qwen_FFN_PF_lut8.mlmodelc
    split_lm_head: 16