| 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 | |