mradermacher/Holo-3.1-9B-Coder-GGUF
LoRA-style vs josephmayo/Holo-3.1-9B-Coder. mradermacher/Holo-3.1-9B-Coder-GGUF is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 8 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 16/32