LCM-Lab/moba_qwen3-4b
LoRA-style vs Qwen/Qwen3-4B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, q_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 108/144
2 derivatives checked
- mradermacher/moba_qwen3-4b-i1-GGUF: Quantization
- mradermacher/moba_qwen3-4b-GGUF: Same weights, converted