mradermacher/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q8_0-GGUF-i1-GGUF
LoRA-style vs Trendyol/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q8_0-GGUF. mradermacher/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q8_0-GGUF-i1-GGUF is a GGUF (IQ1_M) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of attn_k, attn_q, ffn_down, ffn_up changed, in 0 of 0 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Norms 0/257, other 0/1, Attention 3/256, MLP 12/192