bunnycore/Qwen3-4B-Nyx-V6-Minus
Partial fine-tune vs bunnycore/Qwen3-4B-Nyx-V6. Partial change: 47% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 1/1, lm_head 1/1, Norms 136/145, MLP 36/108, Attention 36/144
2 derivatives checked
- mradermacher/Qwen3-4B-Nyx-V6-Minus-i1-GGUF: Quantization
- mradermacher/Qwen3-4B-Nyx-V6-Minus-GGUF: Same weights, converted