Alienstro/Gemma4-E2B-Opus-4.6-Reasoning-3000-GGUF
LoRA-style (fewer layers) vs unsloth/gemma-4-E2B-it. Alienstro/Gemma4-E2B-Opus-4.6-Reasoning-3000-GGUF matches part of unsloth/gemma-4-E2B-it (565 of its 2011 tensors; the rest of unsloth/gemma-4-E2B-it has no counterpart). On the shared part: Alienstro/Gemma4-E2B-Opus-4.6-Reasoning-3000-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 down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 35 of 35 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/247, MLP 105/105, other 0/71, Attention 140/140