samuelcardillo/Qwopus-MoE-35B-A3B
LoRA-style vs Qwen/Qwen3.5-35B-A3B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 10 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 0/1165, lm_head 0/1, Embeddings 0/5, Attention 40/392, other 0/1, Norms 0/247
2 derivatives checked
- mradermacher/Qwopus-MoE-35B-A3B-i1-GGUF: Quantization
- mradermacher/Qwopus-MoE-35B-A3B-GGUF: Quantization