dayuadg/Qwopus3.6-35B-A3B-v1-MTP-GGUF
LoRA-style vs unsloth/Qwen3.6-35B-A3B. dayuadg/Qwopus3.6-35B-A3B-v1-MTP-GGUF is a GGUF (BF16) 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/101, MLP 120/200, Attention 40/40, lm_head 0/1