dnotitia/Smoothie-Qwen3-4B
Same weights, repacked vs Qwen/Qwen3-4B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144
4 derivatives checked
- Alcoft/dnotitia_Smoothie-Qwen3-4B-GGUF: Same weights, converted
- mradermacher/Smoothie-Qwen3-4B-i1-GGUF: Quantization
- mradermacher/Smoothie-Qwen3-4B-GGUF: Same weights, converted
- prithivMLmods/Smoothie-Qwen3-4B-F32-GGUF: Same weights, converted