LCM-Lab/moba_qwen3-8b
LoRA-style vs Qwen/Qwen3-8B. 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, lm_head 0/1
2 derivatives checked
- mradermacher/moba_qwen3-8b-i1-GGUF: Quantization
- mradermacher/moba_qwen3-8b-GGUF: Same weights, converted