autotrust/JEV-9B
Same weights, repacked (fewer layers) vs Qwen/Qwen3.5-9B. autotrust/JEV-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 in different files (re-saved, re-sharded or new metadata).
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/96, Attention 0/224, Norms 0/105
3 derivatives checked
- prithivMLmods/JEV-9B-GGUF: Same weights, converted
- mradermacher/JEV-9B-GGUF: Same weights, converted
- nativ-community/JEV-9B-MLX-NVFP4: Quantization