Mungert/GELab-Zero-4B-preview-GGUF
Full fine-tune (fewer layers) vs Qwen/Qwen3-VL-4B-Instruct. Mungert/GELab-Zero-4B-preview-GGUF matches part of Qwen/Qwen3-VL-4B-Instruct (398 of its 713 tensors; the rest of Qwen/Qwen3-VL-4B-Instruct has no counterpart). On the shared part: Mungert/GELab-Zero-4B-preview-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 130/145, MLP 108/108, Attention 144/144