Verdugie/Opus-Candid-27B-V3.5
LoRA-style vs Qwen/Qwen3.5-27B. Verdugie/Opus-Candid-27B-V3.5 is a GGUF (Q8_0) of different weights. 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 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 192/192, Attention 64/64, Norms 0/161