Mungert/Jan-v1-4B-GGUF
Full fine-tune vs Qwen/Qwen3-4B-Thinking-2507. Mungert/Jan-v1-4B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 90% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 111/145, MLP 108/108, Attention 144/144