h3rb3rn/moe-expert-coder-4b
Full fine-tune vs Qwen/Qwen3.5-4B. h3rb3rn/moe-expert-coder-4b is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 96/96, Norms 0/81, Attention 32/32