mradermacher/Glitch-v1.1-8B-i1-GGUF
LoRA-style vs buzzpy/Glitch-v1.1-8B. mradermacher/Glitch-v1.1-8B-i1-GGUF is a GGUF (Q6_K) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of attn_v, ffn_down changed, in 0 of 0 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Norms 0/65, other 0/1, Attention 16/128, MLP 16/96