blascotobasco/Magnus-16B-A3B
LoRA-style (fewer layers) vs huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated. blascotobasco/Magnus-16B-A3B matches part of huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated (9603 of its 18867 tensors; the rest of huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated has no counterpart). On the shared part: Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 1288/1310, Attention 192/192, lm_head 0/1
1 derivatives checked
- mradermacher/Magnus-16B-A3B-i1-GGUF: Quantization