mradermacher/Qwen3-4B-OBLITERATED-GGUF
Full fine-tune vs OBLITERATUS/Qwen3-4B-OBLITERATED. mradermacher/Qwen3-4B-OBLITERATED-GGUF is a GGUF (F16) of different weights. Fine-tune: 95% of the weights changed, across 34 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 0/145, MLP 102/108, Attention 136/144