| model_info: | |
| name: anemll-Qwen3-1.7B-MLX-dequantized-ctx1024 | |
| version: 0.3.3 | |
| description: | | |
| Demonstarates running Qwen3-1.7B-MLX-dequantized on Apple Neural Engine | |
| Context length: 1024 | |
| Batch size: 64 | |
| Chunks: 1 | |
| license: MIT | |
| author: Anemll | |
| framework: Core ML | |
| language: Python | |
| architecture: qwen3 | |
| parameters: | |
| context_length: 1024 | |
| batch_size: 64 | |
| lut_embeddings: none | |
| lut_ffn: 6 | |
| lut_lmhead: 8 | |
| num_chunks: 1 | |
| model_prefix: qwen | |
| embeddings: qwen_embeddings_lut8.mlmodelc | |
| lm_head: qwen_lm_head_lut8.mlmodelc | |
| ffn: qwen_FFN_PF_lut6.mlmodelc | |
| split_lm_head: 16 | |