shaban2024/Qwen3.5-4B-BOS-Q8-NonThinking
Full fine-tune vs alphaedge-ai/Qwen3.5-4B-bos-32768. shaban2024/Qwen3.5-4B-BOS-Q8-NonThinking is a GGUF (Q8_0/F32) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/81, MLP 96/96, Attention 32/32