andreribeiro87/Qwen3.5-35B-A3B-telco-tracka-GGUF
LoRA-style vs unsloth/Qwen3.5-35B-A3B. andreribeiro87/Qwen3.5-35B-A3B-telco-tracka-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 k_proj, o_proj, q_proj, v_proj changed, in 10 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Attention 40/40, Norms 0/101, MLP 0/200