RecursiveMAS/Distillation-Expert-Qwen3.5-9B
Same weights, converted (fewer layers) vs Qwen/Qwen3.5-9B. RecursiveMAS/Distillation-Expert-Qwen3.5-9B matches part of Qwen/Qwen3.5-9B (427 of its 775 tensors; the rest of Qwen/Qwen3.5-9B has no counterpart). On the shared part: Same weights stored in another dtype (BF16/F32 → BF16).
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/96, Attention 0/224, Norms 0/105
2 derivatives checked
- mradermacher/Distillation-Expert-Qwen3.5-9B-i1-GGUF: Quantization
- mradermacher/Distillation-Expert-Qwen3.5-9B-GGUF: Same weights, converted
10 other repos hold byte-for-byte identical weight files.