XYZAILab/XYZ-Aquila-mini
Partial fine-tune (fewer layers) vs Qwen/Qwen3.6-35B-A3B. Qwen/Qwen3.6-35B-A3B matches part of XYZAILab/XYZ-Aquila-mini (946 of its 31666 tensors; the rest of XYZAILab/XYZ-Aquila-mini has no counterpart). On the shared part: Partial change: 85% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 40 of 40 layers.
Tensors changed: Embeddings 1/4, Attention 253/388, MLP 200/312, Norms 101/241, lm_head 1/1
6 derivatives checked
- bartowski/XYZAILab_XYZ-Aquila-mini-GGUF: Same weights, converted
- IsValorum/XYZ-Aquila-mini-APEX-I-MiniPlus-V2.1-GGUF: Quantization
- IsValorum/XYZ-Aquila-mini-APEX-I-MiniPlus-V2-GGUF: Quantization
- Abiray/XYZ-Aquila-mini-IQ4-GGUF: Quantization
- Guile/XYZAILab_XYZ-Aquila-mini-GGUF: Same weights, converted
- mlx-community/XYZ-Aquila-mini-OptiQ-4bit: Quantization