oselumese/qwen3.5-2B_lora_multidomain-imatrix
Full fine-tune vs unsloth/Qwen3.5-2B. oselumese/qwen3.5-2B_lora_multidomain-imatrix is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 0/61, MLP 72/72, Attention 24/24