DFveloper/gemma-4-26B-A4B-it-qat-q4_0-Claude-Opus-Distill-v2-GGUF
LoRA-style vs 0x795E2795/Obsidian-Alpha-26B-A4B-it-qat-q4_0. DFveloper/gemma-4-26B-A4B-it-qat-q4_0-Claude-Opus-Distill-v2-GGUF is a GGUF (Q4_0) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of attn_k, attn_output, attn_q, attn_v, ffn_down, ffn_gate, ffn_up changed, in 0 of 0 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/271, other 0/32, Attention 103/115, MLP 90/240